TILens Daily Edition 2026-09-22 Filters: topic=ai, github=hidden Stats: 1084 articles, 31 sources, 1024 research papers Top topics: AI, AI Research, Information Retrieval ## News - Better prompt caching for GPT-6 Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/better-prompt-caching-for-gpt-6 - OpenAI GPT-6 Sol and GPT-6 Luna are now generally available on Amazon Bedrock Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/openai-gpt-6-sol-luna-on-amazon-bedrock/ - Introducing GPT-6 Sol and Luna Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/introducing-gpt-6-sol-and-luna - Claude Opus 5.5 is now available on AWS Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/claude-opus-5-5-aws/ - Claude Opus 5.5 is now available on AWS GovCloud (US) Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/claude-opus-5-5-aws-govcloud/ - Turn text input into actions with Needle, a 14MB function-calling LLM Source: raspberrypi-news Topic: Hardware (+AI) URL: https://www.raspberrypi.com/news/turn-text-input-into-actions-with-needle-a-14mb-function-calling-llm/ - Parallel cut research time and cost in half with GPT‑6 Astra Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/parallel-cuts-time-and-cost-with-astra - AWS Security Hub AI Inventory adds Azure self-hosted instance support Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/security-hub-ai-inventory-azure-support/ - Transformers now runs llama.cpp quants Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/transformers-llama-cpp-quants - How UK AISI and EvalEval Are Making Benchmark Results Reproducible Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/evaleval-aisi - Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/omlx - Priorities and principles for effective third party assessments Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/priorities-principles-third-party-assessments - Two bugs my green test suite could not see Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/roshcompanylabs/two-bugs-my-green-test-suite-could-not-see-1eko - 128k context trên desktop là ảo tưởng: KV cache ăn hết RAM Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/128k-context-tren-desktop-la-ao-tuong-kv-cache-an-het-ram-4mnn - Claude Opus 5.5: giá rẻ hơn 20% và 4 breaking change Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/claude-opus-55-gia-re-hon-20-va-4-breaking-change-1kdg - Windows CLOSEDQUORUM malware uses AI models to autonomously select post-compromise actions Source: theregister Topic: General (+AI) URL: https://www.theregister.com/security/2026/09/22/windows-closedquorum-malware-uses-ai-models-to-autonomously-select-post-compromise-actions/5298435 - New Anthropic, OpenAI models make same promise: A little more for a lot less money Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/new-anthropic-openai-models-make-same-promise-a-little-more-for-a-lot-less-money/ - Relays Are Masking Chinese Access to Frontier AI Models in the US Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyber-risk/relays-masking-chinese-access-frontier-ai-models - Event Recap: How AI Agents Solve Large-Scale Problems? Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/event-recap-how-ai-agents-solve-large - 😺 GPT-6 Sol / Luna vs. Claude Opus 5.5 LIVE Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/gpt-6-sol-luna-vs-claude-opus-5-5-live/ - Claude Opus 5.5 wants to finish your coding tasks, not just start them Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-opus-5-5-lifecycle/ - GPT-6 Sol closes most of the alignment gap with Astra. It’s one-fifth the price. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/gpt-sol-alignment-gaps/ - Lawsuit demands OpenAI pay for new school after ChatGPT used in shooting Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/tech-policy/2026/09/lawsuit-demands-openai-pay-for-new-school-after-chatgpt-used-in-shooting/ - OpenAI releases GPT-6 Sol and Luna — and cuts token prices in half Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-gpt-6-sol-luna-release/ - OpenAI launches GPT-6 Sol and Luna, boasting lower cost and fewer mistakes Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/22/openai-launches-gpt-6-sol-and-luna/ - Claude’s merged chat and Cowork vs. ChatGPT’s Work mode: ChatGPT is faster, Claude is more thorough Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-cowork-vs-chatgpt-work-benchmark/ - ABBYY gives old-school OCR a job in the AI pipeline Source: theregister Topic: General (+AI) URL: https://www.theregister.com/applications/2026/09/22/abbyy-gives-old-school-ocr-a-job-in-the-ai-pipeline/5298361 - My thoughts on Jev Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/my-thoughts-on-jev - Anthropic releases Opus 5.5 and cuts pricing by 20%. Your agent calls might secretly get routed to an older model. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-opus-5-5-release/ - Anthropic releases Opus 5.5 with lower prices and Fable-level performance Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/22/anthropic-releases-opus-5-5-with-lower-prices-and-fable-level-performance/ - Stanford's Paper2Agent Turns Research Papers Into Working AI Agents Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/stanfords-paper2agent-turns-research-papers-into-working-ai-agents/ - How OpenAI Built GPT-Live Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/how-openai-built-gpt-live - Five AI safety sessions every founder should have on their TechCrunch Disrupt 2026 agenda Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/22/five-ai-safety-sessions-every-founder-should-have-on-their-techcrunch-disrupt-2026-agenda/ - OpenClaw 2.0 Is Turning AI Agents Into a Multiplayer Workforce Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openclaw-2-multiplayer-ai-agents-vincent-koc/ - Nscale’s IPO will test Wall Street’s appetite for concentrated AI bets once again Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/22/nscales-ipo-will-test-wall-streets-appetite-for-concentrated-ai-bets-once-again/ - Quiz: Using the Claude API in Python Source: real-python Topic: Python (+AI, FastAPI) URL: https://realpython.com/quizzes/using-claude-api-python/ - Quiz: Setting Up Python for Machine Learning on Windows Source: real-python Topic: Python (+AI) URL: https://realpython.com/quizzes/python-windows-machine-learning-setup/ - Don’t be fooled by this summer of AI hype Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/22/1144867/dont-be-fooled-summer-ai-hype/ - Amazon shuts out Meta's Muse Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/amazon-shuts-out-meta-s-muse - 😺 Amazon blocked Meta’s Muse from shopping Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/amazon-blocked-meta-s-muse-from-shopping/ - Altern #25 - The first real launch Source: altern-newsletter Topic: AI (+AI Tools) URL: https://newsletter.altern.ai/p/altern-25-the-first-real-launch - OpenAI Says Its AI Solved 100+ Open Math Problems. Can Researchers Keep Up? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-100-math-problems-researchers-keep-up/ ## Research - Break Your Own RAG Pipeline Before Users Do Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/break-your-own-rag-pipeline-before-users-do/ - Build a Speaker-Recognition App with Claude Code Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/build-a-speaker-recognition-app-with-claude-code/ - 4 Ways to Use AI on a PhD Thesis Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/4-ways-to-use-ai-on-a-phd-thesis/ - An Introduction to Jev Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/an-introduction-to-jev/ - The Ups and Downs of Backprop Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22554 - ST-Topo GAN: A Motor EEG-to-EMG Decoding Model Matched to Wrist Movement Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22128 - Federated Learning for Distributed CNC Tool Wear Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11281 - A discrete generative model of neuronal spiking activity on microelectrode arrays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23907 - The Neural Forcing for Three-Dimensional Incompressible Navier-Stokes finite time blowup Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23934 - RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24972 - Resist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability Switch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22359 - When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08992 - Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23650 - StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22684 - Marginal Calibration Does Not Compose: Hidden Dependence in Modular Robot Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23731 - Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23590 - OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23753 - Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24103 - A Horizon-Independent Regret Bound for Optimistic Hedge in General-Sum Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22839 - R-GEAN: Regimen-Guided Edit Action Network for Within-Admission Medication Change Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22959 - Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22486 - Fast Graph Laplacian Estimation using Effective Resistance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23668 - DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22136 - SCoR: A Hierarchical Framework for Forecasting Relations Between Scientific Concepts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22174 - Causal Localization of the Refusal Direction in Audio Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22260 - Optimal Sample Complexity of Stable Discounted Markov Decision Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2302.07477 - A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22836 - List Counting Failures Are Not One Phenomenon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22230 - Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01699 - Identifying Representational Biases in Datasets Using PCA: A Max-Disparity Partition Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24556 - Vector-Valued Distributional Reinforcement Learning Policy Evaluation: A Hilbert Space Embedding Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18952 - Beyond Task Completion: Training Capable and Safe Computer-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22178 - A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24384 - Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12500 - Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22219 - SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24303 - Information-Time Proximal Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24380 - Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07146 - Critical-State RL: Diagnosing Trainable States for Multi-Turn Tool Use Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24985 - From Latent Biomarkers to Clinical Rules: Embedding-Guided Rule Mining and Attribution-Based Translation for Interpretable Tabular Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22155 - Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22095 - Multiple latent orderings better predict language model preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22170 - Predictors and Orchestrators: Parsimonious Machine Learning within an Agentic AI Harness for Multi-Horizon Karst Aquifer Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22251 - Feature Suppression and Differential Privacy for Residential Traffic Classification: A Two-Home Federated Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23521 - HumynexSurg-1: A Curated Expert Liposuction Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23885 - AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22100 - Enhancing Transformer Representations of Symbolic ODE Expressions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24746 - Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23325 - Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22172 - Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11217 - Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24338 - Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22237 - Connectivity-Aware Exploration of Robotic Grasp Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22983 - Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22254 - Look Before You Steer: Geometry Predicts SAE Feature Steerability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22782 - Data Agents: Agentic Data Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24137 - CNA: An AI-Oriented Comprehensive Normalized Assessment for Healthy Status and Application to Optimize RRT Strategies by Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22232 - Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23703 - Experimental Evaluation of a Low-Power Ultra-Wideband Receiver for Spectrum Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22134 - iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24646 - SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24111 - RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23457 - Correlation-Aware Structured Pruning for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22131 - One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23686 - When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22087 - WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22191 - What Can a Recurrent State Safely Forget? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23366 - CTSpinoPelvic1K: spine, pelvis, ribs and femora in one coordinate frame, annotated for lumbosacral transitional anatomy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22760 - Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20002 - Physics-Informed Classical and Quantum Neural Networks for One-Dimensional Schrodinger Eigenvalue Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22189 - UniK: Universal Knowledge Perception for Digital and Physical AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23971 - Exactness at Inference: A Representational Criterion for Out-of-Distribution Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24942 - Toollery: Scaling LLM Agents to Thousands of Skills and Tools Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22218 - Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23371 - Reinforcement learning with an expectile-based objective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09300 - PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24117 - Optimal No-Regret Learning for Repeated Prophet Inequality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23265 - LE4Mob: Towards Inductive, Distance-Aware and General-Purpose Location Embedding for Human Mobility Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22117 - A Hybrid Quantum Neural Network to Analyse Big Experimental Powder X-ray Diffraction Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22376 - Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23658 - Towards Full Pipeline FP8 Reinforcement Learning for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22870 - Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24440 - Prior-Amortized In-Context Bayesian Inference for Generalized Linear Mixed-Effects Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24422 - Scout: Open-World Species Recognition on the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22897 - Intelligent Degradation Monitoring in Lithium-ion Batteries via Discharge Incremental Capacity Feature Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22843 - SegTSim: A Big Data Driven Segmented Temporal Simulation Framework for Heterogeneous Multivariate Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22192 - MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24736 - Distribution-Free Uncertainty Quantification for Kernel Methods by Gradient Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1812.09632 - OSWorld-Pro: Process-based Evaluation for Computer Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24890 - MolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23073 - ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23659 - ServerlessLoRA: Enabling Low-Latency Serverless Multi-LoRA Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14468 - Connected Content Retriever: Dense Graph Edge Features Powering Pre-Ranking at LinkedIn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22441 - Beyond Final-Token Classification: Heterogeneous Readouts for Evidence-Grounded Suicide Risk Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22767 - Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23260 - P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24138 - Hierarchical Bayesian optimization of an aircraft-based multi-agent system-of-systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22130 - SDC-GON: Singular Decomposition and Consistency-Regularized Green's Operator Networks for Solving Partial Differential Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23206 - Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22349 - Computationally efficient safe exploration in reinforcement learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22919 - Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23163 - When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22337 - PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23574 - Dissecting Hierarchical Reasoning Models: A Mechanistic Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22197 - MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23980 - Reflective Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.03678 - The Undetected Damage of Quantization on Retrieval and How to Fix It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24322 - Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04473 - The Exponential Price of Determinism in Nonsmooth Nonconvex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23837 - From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22224 - Out-of-Distribution Generalization of Risk Aversion in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02755 - Prediction of Nonlinear Oscillations in a Jumping Quarter-Car Model Using Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22205 - Opinion Leader Dynamics: How Sparse Attention Shapes Token Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24202 - A Mathematical Framework and a Suite of Learning Techniques for Neural-Symbolic Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.09693 - Stochastic Flow Map for Count Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23290 - PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24840 - Disassociating performance from compositional feature learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.09716 - Prescriptive SVD-Inspired Attention via Spectral Energy Retention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24370 - Muon Can Outperform Dedicated Continual Learning Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24678 - Conformalized Quantile Regression and Minimax Limits of Fixed-Score Calibration under Known Covariate Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24929 - Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01345 - How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00473 - A Comparative Framework for Evaluating Foundation Models on Tabular Data: A Case Study in Healthcare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22154 - Helix-FNO: Spectral-Domain Operator Learning Coupled with a High-Fidelity Mechanistic Model for Fast Surrogate Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22129 - Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06755 - SPIBER: Reconstructing Free Energy Landscapes from Short, Unconverged Trajectories with Generative Flow Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22663 - Using Composition Operators to Linearize LLM Semantic Transformations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22143 - Online Learning for Dynamic Constellation Topologies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25954 - CleanScore: Black-Box Benchmark Audits with Negative Controls and Sensitivity Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22183 - Neural Residual Modeling for Scientific Data Compression under Guaranteed Error Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23185 - Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22105 - Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23127 - MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24161 - Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21702 - Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23321 - From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23065 - Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22510 - GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24609 - EmbeddGAN: A Novel GAN Framework Using an Embedding Network and Gini Distance Correlation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22508 - JAREX: An Acquisition Function for Multi-Objective Algorithmic Process Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24954 - LPINNs: First-Layer Gated Localization for Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22984 - Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24209 - Scalable Incremental Robustness Analysis of Neural Network Feedback Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22576 - Monotone-Constrained Diffusion Models for Long-Horizon Production Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22643 - Blind Thermodynamic Ontology Discovery from Anonymous Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23387 - Information-Directed Sampling for Causal Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15577 - Adaptive Determinantal Client Scheduling in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23843 - AVTR-1: Open Stack for Real-Time Interactive Avatars Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22913 - Classification with Abstention Under Class-Conditional Error Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22632 - Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24042 - Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05238 - Actionable Insights from Observational Data: The Case of Advanced Classes in K-12 Education Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23836 - Active Inference as a Convex Markov Decision Process Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20152 - A Temporal Knowledge Graph for Music Festival Lineup Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24467 - A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22164 - Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22484 - Rank Portability Does Not Imply Feasibility Portability: Target-Specific Evaluation of Joint Hardware Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22122 - Can Coding Agents Reproduce Official Statistics? Metadata, Retry Budget and the Limits of Execution Feedback in a Controlled Eurostat Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22222 - On attention heads and bilinear forms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22990 - ZoAQ: Adaptive Zeroth-Order Querying via Query-Reuse Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22115 - Scaling Articulated Rationales for MLLM-based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.17639 - Scoring With the Engine: Retrieval Exposure, Cross-Engine Divergence, and the Limits of Engine-Agnostic GEO Scores Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22655 - Understanding Mobile App Recommendation Dynamics in General-Purpose LLMs: An Empirical Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.18364 - Efficient K-generalizable Learned Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.06159 - Bridging Static and Agentic RAG for Taiwanese Historical Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23056 - FlowRec: Prior-Informed Flow Matching for Efficient Sequential Recommendation Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2508.17618 - DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research, JavaScript, React) URL: https://arxiv.org/abs/2609.22104 - Auditing Source Exposure in Baidu and Google AI Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24407 - Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.28886 - Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.07449 - UK-PRBENCH: A Paragraph-Level Precedent Retrieval Benchmark for United Kingdom Case Law Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24613 - Explainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23877 - Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23646 - Beyond Raw Engagement: A Counterfactual Observability Framework for Recommender Systems at Netflix Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22747 - Checkpoints Are Not Enough: Trust Calibration in CoSLR, a Human-AI System for Systematic Literature Reviews Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22248 - Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23880 - Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24620 - Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.13095 - From Prompt to Recommendation: A Fitted Stage Model of Brand Visibility in AI Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23162 - Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23307 - IntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22529 - Inherit4Rec: Parameter Inheritance for Efficient Scaling of Recommendation Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23111 - Improving disruptive research in the EU: why strengthening European Research Council grants alone is not enough Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23115 - How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.28358 - LIGE-GR: A Smooth Leap from Ranking to Generative Recommendation in the LLM Era Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18148 - Graded-Relevance Composed Multimodal Retrieval for E-commerce Visual Search at Scale Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24152 - UNIQUE: A Unified Retrieval and Ranking System for Large-Scale Feed Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23718 - DOA-SORT: Directional Occlusion-Aware Multi-Object Tracking with Distributional Observations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22706 - When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24101 - Attributable Post-Rationalization in RAG Citations: A Controlled Reproduction and an RLVR Comparison Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23053 - A Redundancy Reduction Approach for Controllable Sequential Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23849 - What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.24430 - Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2505.13994 - Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2509.11353 - Algorithmic Collusion and the Complexity of Information-Value-Free Equilibria Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22757 - When Does Learning Beat Heuristics? A Case Study in Kubernetes Scheduler Score Plugins Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22142 - Low-Rank Frequency Convolution and Noise-Range Augmentation for Real-Time Pitch Estimation on Edge Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23340 - Toward Fairness in Machine Learning Models for Predicting Treatment Retention and Premature Discontinuation in Medication for Opioid Use Disorder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22113 - User-Level Handover Decision Making Based on Machine Learning Approaches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22593 - Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23917 - PROSE: A Theory of Optimal Stopping with Perishable Evidence for Peer Selection in Intermittently Connected Decentralised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23845 - Contrastive World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22175 - Optimizers for Diffusion Models: A Controlled Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23055 - CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23320 - Merge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22886 - In-context learning from self-generated trajectories for adaptive model reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02937 - Joint Domain-Class Modeling for Federated Learning Under Feature Skew Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22932 - Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22088 - TTSE: A Two-Track Online Self-Evolution Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24289 - An Empirical Survey and Benchmark of Learned Distance Indexes for Road Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04068 - EvoRank: LLM-Guided Evolution of Multi-Objective Learning-to-Rank Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22196 - A Synthetic Multivariate Refrigerator Time-Series Dataset for Predictive Maintenance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22229 - Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23008 - A Distributional Optimisation Perspective on Combining Models in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24328 - Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22144 - TARGet: Topology-Aware Fusion-based Radio Frequency Circuit Functional Modeling using Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22165 - Event Signature Transfer: Model-Agnostic Forecast Scenario Construction from Historical Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23074 - Uncertainty and Business-Aware Remaining Useful Life Estimation for Semiconductor Manufacturing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22160 - CALM: A Calibrated LLM Choice Network Framework for Activity-Based Traveler Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22252 - RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24464 - BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04798 - Machine Learning for Underwater Optical Wireless Communication Systems: A Comprehensive Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22294 - 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24432 - KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24298 - Benchmarking Hybrid Deep Learning Architectures for Predictive Maintenance in Industry 4.0 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22583 - Credit Access is Associated with Improved Food Security in the Horn of Africa Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24382 - Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22101 - A Channel-Boosted Multi-Agent System with Iterative Consultation for Document Sensitivity Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22212 - FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24089 - On the Information-Theoretic Limits of Latent-Space Watermarking Through Pretrained Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24377 - Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22097 - Common Cause, Not Cross-Attention: Blocking Visual Shortcuts in Audio-Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22361 - StyleAT: Defending Face Recognition Against Semantic Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23596 - CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18451 - Artificial Structure Function Search: Preserving Artificial Functional Connectivity for Structured Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24401 - Negation-Aware Weighted Information Fusion for Reliable Evidential Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00754 - Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24882 - Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22220 - Scikit-fingerprints: Python library for scikit-learn compatible molecular fingerprints and chemoinformatics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02027 - NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24391 - The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22156 - Complexities of Weak Proximal Oracle Methods for Composite Convex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24423 - Dropout Neural Network Training Viewed from a Percolation Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13853 - ORION-CMR: On-scanner Reporting with Integrated Foundation Model for End-to-End Cardiac MRI Analysis and Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23950 - Forecasting Intrathecal Tracer Enhancement from Pre-Contrast Brain MRI: Direct Regression versus Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22377 - Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23215 - STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23716 - Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24791 - Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22225 - Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22120 - Beyond Point Prediction: Artificial Representative Trees with Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24528 - FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22816 - MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23990 - Gradient-estimator design overcomes trainability barriers in neural-network-based variational optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22342 - Silent Failures at the $2^{32}$ Boundary: A Technical Report on Large-Tensor Matrix Multiplication in PyTorch's Apple MPS Backend Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22991 - Acceptance-Aware Draft Model Training for Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24150 - Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24754 - Bayesian Deck-of-cards-based Ordinal Regression with Sequential Preference Elicitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23212 - Signal-Informed Temporal Routing for Vinyl Defect Regime Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23164 - Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.16139 - A Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23333 - onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24983 - Glass-Box Deep Learning for FDIA Detection in Nonlinear Automatic Generation Control: A Kolmogorov-Arnold Network Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05259 - Complex-valued Phase-Coherent Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22415 - Machine Learning-Based Prediction of Childhood Stunting in Bangladesh: Fairness and Temporal Robustness Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24386 - Generalized Multimodal Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22107 - Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23117 - Offline Reinforcement Learning for Distribution-Grid Protection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24703 - Replication Without Persistence in Hosted LLMs: Measurement Sensitivity in Action-Time Belief Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22478 - Mobile Imaging Solutions for Medical Diagnosis: Trends and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24814 - Unlocking Pretrained Vision Transformers for Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.08641 - SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23353 - Lifted Bellman Linear Programming for Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24489 - Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23383 - When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24862 - Adversarially Robust PAC Learning with Optimal VC Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24260 - Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22161 - Generalised Balanced Softmax: A Finite-Data Perspective on Logit Adjustment for Long-Tailed Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22258 - GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22146 - Graph-to-Grid (G2G): Continuous-Coordinate Feature Painting for Soccer Pass Surfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24040 - Strategic Classification Has a Missing Lever: Audit Risk Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22534 - Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22103 - Reinforcement Learning in Operational Research: A Technical Review and Practical Roadmap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24750 - CLOOPD: Closing the Learner Loop in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24141 - HFEMCNet: A Compact Hybrid Frequency Enriched Multi Channel Network for Automatic Modulation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22139 - Density-Ratio Rescoring for Imbalanced Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23926 - Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Efficient Instruction Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22943 - SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22233 - Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22149 - Learning-Based 3D Reconstruction of Power Networks from Aerial Point Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23915 - The Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22195 - A Shared Learning Rate Is Not a Neutral Control in Selective On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22109 - G-NAC: Graph Neural Automata Clustering via Emergent Domain Formation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24823 - Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22879 - Improving Parameter Utilization by Sharing Neural Experts Across Layers in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22199 - Predicting Out-of-Distribution Generalization of Neural Operators via Observable Spectral Error Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23529 - Stealing profits: Spread-based temporal hierarchy forecasting for day-ahead electricity markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23223 - Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03434 - RheOFormer: A generative transformer model for simulation of complex fluids and flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01365 - Gaussian Process Decorrelation for Spatiotemporal Deep Learning-Based Snow Water Equivalent Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22182 - Task-Aware Hybrid QUBO Optimization for Structured Neural Network Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22238 - Proximal Residual Value Functions for Consistent Planning and Real-Time Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23242 - Summarize, Judge, Refine: Decoupled Content Understanding and Policy Learning for Multimodal Content Moderation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22094 - Adaptive Physics-Informed Neural Networks for the Blasius Boundary-Layer Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22185 - Overlay\_dx - Automating forecasting evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24586 - Discovering Physical Representation Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23381 - Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13172 - Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24379 - Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24249 - Exponential Family Synthetic Controls Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23970 - Learning tactile perception from high-bandwidth single-point sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24621 - Causal Bayesian Optimization: Foundations, Methods, and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24112 - PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23449 - CHART: A Harness-Rotation Curriculum for Harness-Robust Search Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22247 - Do Student LLMs Inherit OOD Robustness? Invariance-Weighted Distillation for Reliable Knowledge Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22566 - Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24517 - Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24241 - Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24579 - Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23085 - Causilo Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22866 - Learning and Control Beyond Linearity: Towards a Non-asymptotic Theory for Bilinear Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22338 - Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23789 - CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23257 - Conformal Robustness in Prediction-Driven Decision-Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23170 - The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23374 - Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11318 - Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24146 - GenVoid: Uncertainty-Aware Learning of Subsurface Material Defects with an Experimentally Validated Physics-Informed Generative Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23761 - Counting and Covering in Nearest-Neighbour Representations of Boolean Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23094 - A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22194 - Noise-Debiased Thermodynamic Variance for Local Learning Coefficient Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22389 - Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23385 - D-JEPA: A Decision-Aligned Latent World Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24749 - Matched-Input Estimates Differ in Sign Across Architectures: Auditing EEG Foundation Models on Motor Imagery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23924 - ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23314 - ShapeLex: Decoupling Local Shape Symbolization and Global Scale Modeling for Text-Controlled Time Series Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24003 - Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24064 - Towards Robust Classroom Attendance: A Comprehensive Evaluation of Face Detection and Recognition Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22750 - Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22234 - Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23334 - Clustering-Based Collective Anomaly Detection in IoT Systems: A Graph Neural Network Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22166 - WiNeRF: Measurement Constrained Radiance Fields for Actionable Wireless Channel Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22132 - Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23594 - Sparse Regression Distilled from a Single Robust Fit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23937 - Streaming Deep Reinforcement Learning Finally Works Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.14606 - Time Series Foundation Models for Process Model Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07624 - Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22162 - Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24480 - The shape of quark flavors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22812 - VISTA: An Attention-Based Multi-Agent Reinforcement Learning Architecture for Space Situational Awareness Sensor Tasking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23875 - Auditing Bayesian Graph Alignment: Diagnostic Comparisons and Reference Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23232 - The Effect of Quantization on Clinical Benchmarks: Accuracy and Safety Across Model Families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22216 - Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22257 - StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22123 - MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24455 - OSCAR: Order-aware Scoring and Calibration for AI Rankings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24128 - RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22258 - ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22771 - UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22217 - Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22819 - Augmented Hypothesis Testing with Persona-Based LLM Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24629 - High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24278 - Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22206 - Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23688 - Are Coreset Selection Methods Worth Their Cost? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22894 - TRACE: Tractable Routing Autoencoder for Clinical ECG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23460 - Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24302 - Evaluation Awareness Shifts from Format to Context with Model Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22119 - COREM: Cosine-Relation Momentum Reshaping with Stateful Writeback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22487 - TAC-Time: Texts as Channels For Multimodal Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24156 - Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23697 - TWIG: A Time-Causal Wavelet Operator for Autoregressive Forecasting on Irregular Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22585 - Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23812 - Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24443 - Fractal basin geometry and the limits to predictability and reproducibility in deep learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05606 - ITSY: Causal Discovery From Irregular Time-Series Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23516 - $t_0$: A Time-Series Foundation Model for Forecasting with Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24559 - Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24233 - SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22153 - Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02626 - Watching Quantum Models Think: Hilbert-Space Interpretability in Quantum Transformer Blocks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23016 - Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22173 - XSQ-AST: An Explainable Audio Spectrogram Transformer Framework for Localising Synthetic Speech Artifacts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24770 - Augmenting PID Control with Deep Reinforcement Learning: A Hybrid Approach to the Industrial Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22584 - LoRA-generating hypernetworks for efficient on-device LLM generative personalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24979 - PRQuant: Permutation Residual Quantization for Low-Overhead Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22106 - Concurrency-Aware Process Model Forecasting with Causal Nets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22614 - Efficient Mixture-of-Experts with Speculative Decoding via Expert Coactivation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22471 - Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24397 - Multi-Armed Bernoulli Bandits via Minimax Single-Arm Stopping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22690 - Correlation-Guided Flow Matching with Annealed Masking for Spatial Transcriptomics Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22187 - Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22209 - When Calibration Depends on the Scoring Rule: Quantized Biomedical LLM Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03854 - An LLM-Assisted AutoML Framework for Intrusion Detection in IoT Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23097 - Clinical Domain Classification from Medical Transcriptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22734 - Rare Event Estimation via Iterative Unalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24969 - Learning Physics from an Imperfect Ancestor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24947 - Contrastive Siamese Representation Learning for Predictive Maintenance of Electrical Submersible Pumps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22360 - Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23967 - Decoupled Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23535 - DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26446 - Online Learning of Scale Parameters in Score-Driven Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09218 - Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22188 - Logits are All We Need to Adapt Closed Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.06806 - Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23999 - If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23376 - Interpretable Stress Detection from ECG Signals Using Motif-Based Anomaly Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22179 - Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23269 - Taking a Second Look: Correcting Sea Ice Forecasts with Sparse Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24591 - Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11508 - Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22226 - A Bayesian Vertical Federated Learning Framework for Multivariate Reduced-Rank High-Dimensional Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22654 - Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24651 - Global Ranks Survive, Selected Heads Shift: BOS-Sink Topology under 4-bit Weight-Only Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23585 - RLVR is a Kernel, Not a Function: Statistical Inference for pass@$k$ Crossovers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22547 - On Emergent Capabilities and Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24504 - Optimal Multi-way Decision Trees for Stratified Sampling in Online Controlled Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23308 - PAGE: Partition-Aware Gated KV-Cache Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22157 - Improved Private Sparse Covariance Estimation with Multiscale Threshold Tests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22783 - ARM: Attention with Routed-Memory for Learnable Sparse Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24417 - Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22867 - Leakage-Safe Empirical Benchmarking of EEG-Based Machine Learning Pipelines for Dementia Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22092 - ECP-Bench: Benchmarking and Learning Entertainment Content Promotion with Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22150 - When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22299 - Luck Is Not Skill: When Do Paired Rollouts Help Group-Relative RL of LLM Agents? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24144 - Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22880 - Explainable Predictive Condition-based Maintenance of Naval-Propulsion Systems using Fuzzy Logic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24250 - CAMFT: Conflict-Aware Mergeable Fine-Tuning for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22253 - The Price of Self-Calibration: Exact Evidence Budgets and Manufactured Blind Sets in Adaptive Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23254 - Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22138 - Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23146 - Output-Aware Rotation for INT2 KV-Cache Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02691 - From Regional to Global: Transfer Learning for Atmospheric Transport Emulators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23838 - CLEAR: Complex Learned Explicit Analytical Regularization for Ultra-Accelerated 4D Flow CMR Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22950 - WPBench: A Comprehensive Benchmark for Wind Power Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24444 - One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23377 - Real-time Generalizable Heart Valve Mechanics for Clinical Disease Assessment via a Physics-Conditioned Neural Operator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23826 - Model-Agnostic Feature Selection via LOCO-Guided Adaptive Minipatch Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24126 - Testing the Construct Validity of a Functional Valence Axis in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22850 - On Dominant Manifolds in Reservoir Computing Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05967 - Poisson Exchange Beyond Submodularity: Effective Approximation Algorithms for Offline and Online Subset Selection over Matroids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24569 - BadWAM: When World-Action Models Dream Right but Act Wrong Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15207 - Do Language Models Know Their Own Constraints? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22151 - Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23775 - Correcting Learning-based Perception for Safety Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22108 - Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23017 - Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24021 - GDN Tree-Scan: Served Tree Verification for Recurrent-Hybrid Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23900 - SiST-GNN: Simultaneous Spatial-Temporal Message Passing for Dynamic Graph Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25548 - Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23547 - The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23988 - Holographic generative flows with AdS/CFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22033 - Falling Trees: A Model Class for Interpretable Risk Prioritization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23780 - Modelling daily activity patterns from mobile phone location data via deep representation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22121 - Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23038 - Quantifying Hidden Salt for Precision Healthcare: Sodium Assessment via Joint-Factor Retrieval and Chain-of-Thought Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22171 - DPTM-DT: Dual-Pretrained Transformer Multitask Representation Learning for Drug-Target Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22184 - ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19893 - Directional Linear Separability of Neural Representations: Geometry and Transformations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08721 - Locally Private Inference for Riemannian Stochastic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22642 - AutoGym: Blueprint-First Generation of Verifiable Agent Gyms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22592 - When Does Adversarial Refinement Help? A Negative Result and Open Problem in Adapting R3GAN to Time Series Imputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23102 - Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22977 - Guaranteed Low-Rank Tensor Recovery from Modewise Measurements via Normalized Block-Weighted Riemannian Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24679 - SPID: Distilled Protein Backbone Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03095 - Assessing Adversarial Robustness of Latent Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22228 - Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23087 - H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24197 - Universal Observatory Graphs for Distributed Sky Coverage and Artificial Intelligence Based Interplanetary Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22244 - Label Propagation for Physics-Informed Neural Networks and Physics-Informed Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.05817 - Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23476 - On Generalized Naive Bayes with Continuous Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23819 - ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22323 - A Federated Artificial Intelligence Framework for Optimizing Pancreatic Cancer Treatment - Strategy Update Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24718 - Role-Aware Morgan Fingerprints for Reaction Yield Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22167 - Physics-residual machine learning predicts oxygen-evolution catalyst activity beyond the training range from sparse polarization measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23549 - Circuit-Diff: Factual Edit-based Intervention Method for Localizing Knowledge in Attribution Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23892 - Robust Market Making with Hawkes Order Flow and Price Impact via Adversarial Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22785 - Transductive Off-policy Proximal Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.03894 - Guiding the coarse levels of semantic IDs makes the fine levels learnable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22227 - TEMPER: Temporal Encoder-Masked Probabilistic Ensemble Regressor for Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23701 - A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01028 - Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22240 - Replicating the Geometry of Emotion Representations in a Base Open-Weights Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22208 - The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23092 - Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23995 - On Mitigation of Subliminal Learning in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22215 - TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.23766 - Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23141 - Perplexity Cost Understates What Activation Quantisation Breaks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23125 - Personalized Federated Reinforcement Learning via Model-Agnostic Meta-Learning: Convergence of Exact and Hessian-Free Meta-Policy Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22833 - Collaborative Streaming Anomaly Detection with Interactive Explanations and Ensemble Consensus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23883 - Large language models in medical time series analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22262 - Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2502.01562 - StepKV: Step-Aware KV Cache Compression for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22158 - Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24280 - GLR-MM: Graph-Based Global-Local Reconstruction for Robust Multimodal Chest X-ray and EHR Representation Learning under Missing Modalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23876 - Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24797 - Mask-Aware Execution for Efficient JEPA Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22674 - MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24441 - A multi-temporal dataset for mapping burned areas in the Brazilian Cerrado using time series of remote sensing imagery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23687 - EAVer: Long-Form Factuality Verification as an End-to-End Agentic Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22223 - ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23582 - Autonomous Model Lifecycle Management for Digital Twin-Based Manufacturing Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22701 - Robot World Models Are Not Invariant to How the Actions Are Written Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23252 - CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08029 - Attention-Enhanced Dual-Branch ConvNeXt-BiLSTM Network for Subject-Independent EEG Seizure Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22141 - AirGC-CD: Gaussian-Circulant Precoding for Exactly Debiasable PAPR Reduction in Over-the-Air Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23084 - K-TRAIL: Simulator-Guided Generative Design of EM/RF Circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23183 - Multivariate quantile regression via Kolmogorov-Arnold Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23906 - Causal Inference with Unobserved Confounding: A Mixture Learning Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23219 - CurvFlow-DTA: dual-graph discrete Ricci curvature flow for drug--target affinity prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22862 - Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23986 - Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02069 - Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23435 - Optimal Symmetries in Binary Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.08823 - D-IMPL: A Diffusion-based Solver for Parameterized BBOs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22752 - Weak Ties, Strong Signals: Efficient Training Data Detection in Diffusion LLMs via Independent Token Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22145 - Discretization-independent operator learning for partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.07292 - An Exact Junction-Tree Extended Formulation for Optimal Classification Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24741 - RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.07977 - Focused PU learning from imbalanced data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14467 - Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10925 - The Illusion of Improvement: Reject Inference Strategies in Credit Scoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18479 - A principled approach for energy-efficient training via phase-aware GPU frequency tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24205 - Training Non-Differentiable Networks via Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01928 - WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23033 - AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22951 - Anatomy of a Closed-Loop Collapse: A Causal Case Study of a Compressed VLA Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23048 - Explainable Neuro-Fuzzy Prediction for Trustworthy Decision-Making in Maritime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24358 - Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23415 - Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07419 - SAGE: Optimal-Stopping Peer Selection for Decentralised Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23773 - SolarFlowRefiner: Refinement-Aware Flow Matching for Surface Solar Radiation Downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22126 - OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22177 - MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24259 - Beyond Average Error through Oracle-Informed Stress Tests for Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22820 - Climate Variability Modulates the Impact of Price Spikes on Food Insecurity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24394 - Large Language Model Agents for Evidence Based Genetic Disease Severity Classification Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.19569 - Reinforcement learning for post-coronagraphic wavefront control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20880 - AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12374 - AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21192 - Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese Web Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07699 - Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22754 - Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00285 - Samsone: A Family of Open Small Audio Language Models for On-Device Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21666 - Neural Cellular Automata Learn General Features in their Hidden Channels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21870 - Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13571 - Beyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21599 - Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00442 - OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21550 - Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21276 - Matrix AdaGrad: Row-wise and Column-wise Adaptive Subgradient Methods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21815 - Understanding Structural Representation in Foundation Models for Polymers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.11881 - Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08797 - Touvigation: Embodied Adaptive Object Acquisition for Blind and Low-Vision Users in Unfamiliar Indoor Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21828 - Continuous Spiking Graph Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.01897 - Efficient Benchmarking in Production: A Study of an Evolving LLM Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21267 - Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21094 - Chinese Competitive Debating Dataset and Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21637 - A Training-Free Proactive Defense Against Partial Speech Manipulation via Self-Embedding Steganography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25285 - Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16086 - PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30378 - Collaborative Memory for Multi-Agent VLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17921 - When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21942 - Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21381 - LLM-Generated Feature Pools for Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21801 - HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00993 - CaLR: Causal Latent Revision for Robust Diffusion Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20981 - Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21997 - CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21344 - A primer on evaluation methods for large language models in healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14819 - TabScope: Question-Adaptive Scope Selection for Table Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03395 - HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21484 - From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.21349 - SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20899 - The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21133 - NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20323 - MemeLens: Multilingual Multitask VLMs for Memes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12539 - VLA-Scope: Shift-Aware Failure Prediction for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21246 - CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21259 - Reinforcement Learning under External Influence: Guarantees, Algorithms, and Sample Complexity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2305.16056 - ForceTwin: Physics-informed Digital Twins for Robotic Manipulation from Instrumented Human Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21751 - Metric Self-Dual Completion and Optimal Additive Hardness for Quantum and Graph-State Distance Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.22669 - Evaluating Decision Models for Text Annotation in Computational Social Science Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24574 - Correct Diagnosis, Better Feedback: A Symbolic-Verifier for Faithful LLM Tutoring Feedback in Logic Proofs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22553 - Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23551 - Machine learning and digital pragmatics: Which word category influences emoji use most? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21975 - LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18082 - Configurable Multi-Stage Vision Pipeline for Crop Disease and Pest Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21651 - A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18193 - STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13165 - Team DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22221 - Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06634 - A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12538 - On the Efficiency-Safety Dilemma in Large Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23587 - HaikuS2S: A Cascaded System For Responding In Verse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23951 - Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24895 - URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24372 - RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15364 - Initial Evaluation of Potential Bias in Coverage of Humans in Wikidata Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.22375 - The Corroboration Illusion: When More News Makes LLM Forecasts Less True Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22246 - AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23979 - Memory vs. Context? Influential Factors of Factual Recall in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24238 - Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22452 - Fallacy Benchmarks Measure Scheme Recognition, Not Fallacy Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18644 - Measuring the Assistant's Harmlessness Preferences on the User Turn Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23935 - Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01532 - The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22214 - Rethinking Pivot Programming Languages in Code Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22988 - PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22200 - Agora: Git as Shared Memory for Collective AutoResearch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18094 - Information-Geometric First-Passage Monitoring of Distributional Stability in Stochastic Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24083 - Calibrating Lightweight Sparse Autoencoder Feature Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12576 - Monocultural Biases: Correlated biases in large language models lead to unequal systemic exclusion rates in hiring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22169 - MIS-Bench: Benchmarking Multimodal LLMs for Psychotherapeutic Interpersonal Skills Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22778 - Revisiting Lexicon Evaluation in Unsupervised Word Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06183 - You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04945 - SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24911 - Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24657 - The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01161 - AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22796 - Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11161 - The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24821 - Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12122 - When Residualization Helps an Audit: Format Effects, Slice Gains, and Their Limits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24194 - HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08494 - A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22249 - Automatic multimodal UX improvement recommendations from LLM agent user simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22971 - LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24196 - Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.08038 - Evaluating Fine-Tuned and Base Language Models in Maternal and Vaccination Healthcare for African Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22110 - Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24327 - An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database Source: arxiv-cs-cl Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2609.22917 - A Course Intelligence Platform for Higher Education: Lessons from AI-Assisted Course Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.02455 - You Can Tell Who's Asking: What the Web's Questions Are Made Of, and Where They Come From Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24106 - M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22172 - Contributions to the hierarchy of probabilistic languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23567 - The BD-LSC Dataset: Facilitating the Benchmarking of Models for Lexical Semantic Change Detection in Slang and Standard Usage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16560 - A frontend-backend architecture for tool calls in full-duplex speech models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19334 - ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00468 - Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14089 - Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22261 - VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.00852 - BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22235 - Length Penalties Make Chain-of-Thought Less Monitorable Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09786 - Who Should Be Generated? Justifying Demographic Targets in Open-Ended Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02551 - From Articles to Publishers: Aggregating Language Model Predictions for News Source Reliability Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24219 - MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24812 - The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24885 - RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22000 - AI-inferred expressed well-being and collective-action discourse in climate-change campaigns on X Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22096 - When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22522 - Can LLMs Reason in a Legally Meaningful Manner? A Small-scale Study on European Court of Human Rights Cases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17168 - BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17904 - SALSA: Semi-Autonomous Literature Summarization Assistant Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22210 - Decomposing Error and Style in Automated Clinical Coding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24877 - Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23465 - Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22152 - Riemannian Geometry for Pre-trained Language Model Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07047 - Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yemba Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23194 - VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23570 - CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22494 - CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13387 - Rubric-Guided Process Reward for Stepwise Model Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29310 - this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23886 - LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23193 - What are Key Factors for Updates in RL for LLM Reasoning? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22570 - Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06487 - The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21008 - XYEval: Agents say yes to bad advice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23939 - Who's Behind It? Annotating and Extracting Conspiratorial Actors from German Telegram Posts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04962 - An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22114 - LLJ Cards: Best practices for the Use of LLMs as Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24516 - Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23463 - Assessing Readability with LLMs: The Role of Reasoning and Few-Shot Prompting Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.24650 - Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.22124 - Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22603 - Decomposing Refusal Steering in Mixture-of-Experts Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04160 - LLMs Anchor on Chief Complaint and Fail to Integrate Evidence in Sequential Clinical Triage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22904 - SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24894 - Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15322 - FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23808 - Morpho-VITS: Variational Inference with Morphological Modeling for End-to-End Speech Synthesis of a Tonal Bantu Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24310 - ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17945 - MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22163 - ILRR: Inference-Time Steering Method for Masked Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21647 - NLPCC 2026 Task 10: Citation-Level Faithfulness Verification with DeBERTa Ensembles and Class-Wise Calibration Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.22774 - The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28190 - CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19189 - Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.07044 - Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22362 - COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22697 - Extracting Arguments, Not Just Classifying Them: Instruction-Tuned LLMs for Generative Component Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24855 - Low resource cross-modal alignment using HGNN to enhance speech representation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23191 - LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04733 - Reasoning Reduces the Influence of Poisoned Context in RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17153 - Pretrained Persona Mixture Models and Tandem Models for Human Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22607 - DolphinBench: Mapping the Pareto Frontier of Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24971 - English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13286 - X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09632 - Directing large language models to follow the letter or spirit of the law Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23083 - Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22793 - Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03262 - Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23959 - Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24698 - Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19805 - H2LooP Telecom Model v1: From Telecom Comprehension to Autonomous Issue and PR Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22241 - Representation-guided in-context learning for medical image interpretation with multimodal large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24057 - QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24538 - Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.05880 - Mitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24357 - Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24199 - MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23416 - Do Chess Explanations Reflect Model Decisions? Behavioral and Token-Level Tests of LLM Reasoning Faithfulness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22245 - Harness-Zero: Harness Distillation via Agent-as-Harness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24974 - Knowledge Graph-Augmented Ambient AI for Clinical Note Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22239 - Authorship identification under domain shift: a survey of stylistic measures and learned author representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.00436 - Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24264 - GRACE: Grounded Adversarial Reasoning over Canadian Law Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23726 - Analyzing Public Discourse on Urbanism: Topic Clustering, Sentiment Analysis and Retrieval-Augmented Generation using YouTube Comments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22705 - Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22920 - Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.24122 - From Outliers to Topics in Language Models: Anticipating Trends in News Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22030 - EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22231 - Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01654 - Error-Supervised Synthetic Learner Writing for Automated Essay Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23573 - RADAR: Retrieval-Augmented Detector with Adversarial Refinement for Adaptive LLM-Generated Fake News Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03981 - Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev) Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24052 - Which Part of the Context Layer Does the Work? Separating Semantic Content from Retrieval Scaffolding in Text-to-SQL Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22259 - When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22102 - GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21562 - Linguistic Features for Interpretable Textual Entailment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24932 - SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.17021 - From Noise to Signal: When Outliers Seed New Topics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18358 - Characterizing Model-Native Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17614 - Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16390 - AdaMame: A Training Recipe for Adaptive Multilingual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15080 - Type-Driven Tokenization for Brahmic Scripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22125 - Evaluating Personal Information Output from Conversational Interactions in Generative AI Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22204 - Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23043 - When Evidence Conflicts: Reliability-aware Meta-review Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24028 - Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22949 - SCoP: Structured Constraint Parsing for Evidence-Space Control in Temporal Knowledge Graph Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22213 - Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18389 - Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23267 - Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22934 - Custom Named Entity Recognition and Topic Classification for Global Health Publications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24625 - SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00689 - Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27339 - Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23039 - A framework for recipe data structure with applications for culinary and nutritional insights Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22099 - Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.24177 - A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04409 - MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12916 - Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22090 - Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09175 - The Role of AI in Online Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22198 - Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01733 - Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06787 - Cross-Dialect NER for Bangla Regional Dialects Using Leave-One-Dialect-Out Cross-Validation and Explainable AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22536 - Toward a Unified Mathematics of Concepts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24554 - RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23466 - From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08899 - Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23205 - HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16353 - HearInContext: A Benchmark for Implicit Context in Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18680 - LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22700 - Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22243 - Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.10163 - BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27110 - SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03351 - A vector logic for intensional formal semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02940 - Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25920 - Judging a Review by its Cover: A Reliability Analysis of LLM-based Peer Review Evaluation Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23264 - AskQE: Question Answering as Automatic Evaluation for Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.11582 - SoK: Formal Methods for Fact-Checking and Information Integrity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23239 - Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04192 - AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05435 - Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20777 - TempCore: Are Video QA Benchmarks Temporally Grounded? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.01167 - SingProbe Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30703 - TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22098 - LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23367 - Provenance Before Prose: Claim-Locked Reporting for Statistical Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25336 - ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24903 - Beyond the Text: Verifying That Agent-Written Papers Are Backed by Their Artifacts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22111 - Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23592 - UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20630 - Can Generalist Agents Automate Data Curation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04261 - CCTU: A Benchmark for Tool Use under Complex Constraints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15309 - Toward Personalized Sleep Guidance from Wearable Data Using Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22463 - SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23713 - Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08974 - Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23825 - From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23966 - VERPO: Verified Evidence Regularized Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06100 - Trustworthy FinAInce: Unpacking How AI-Mediated Financial Advice is Judged Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20989 - Memory That Looks Forward: A Zero-Inference Prospective Term for Personal Memory Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22091 - Chronologic: Measuring Language Models' Ability to Represent the Past Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23178 - Apollo Restore: A Foundation LLM for Historical Greek Optimized for Fill-in-the-Middle Restoration of Ancient Greek Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22455 - BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23490 - Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24066 - BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04919 - TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27690 - Some Dialects Are More Equal Than Others: Non-Prestigious Arabic Dialectal Bias in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23955 - ChemCLIR-Bench: Benchmarking Cross-Lingual Information Retrieval in Multilingual Chemical Patents Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.23231 - Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24965 - Observational Equivalence of LLM and Human Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22133 - Evidence for systematic semantic structure in individual letters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17306 - Explain Less, Understand More: Data-Efficient Personalization of Reader-Dependent Jargons Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.16227 - Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22135 - Beetle: A Bilingual Model Suite for Modelling Second-Language Processing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22633 - Emergent Collusion in Long-Horizon LLM Agent Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24967 - MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00842 - An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13624 - Xeno-Interpretability: Investigating the Alien Minds of LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20408 - Beyond Accuracy and Surface Fluency: Risk-Sensitive Evaluation of LLMs for Legal Clause Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22127 - Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10893 - DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22256 - OmniEdu: Open Foundation Models for Learning and Teaching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23088 - 3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.16698 - VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03203 - From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24083 - Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22419 - Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track~1 System for the NVVSpeech Challenge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23462 - Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04186 - End-to-end Jordanian dialect speech-to-text self-supervised learning framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24410 - Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.11809 - Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24635 - Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24246 - Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01432 - Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22255 - Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16800 - Structure Before Sampling: Community-Aware Core-Set Selection for Data-Efficient Text-to-Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24275 - Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22112 - What Is The Political Content in LLMs' Pre- and Post-Training Data? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22367 - What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04720 - Block-Sparse Attention with Semantic-Geometric Decoupled Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22884 - Tutoring Large Language Models to be Domain-adaptive, Precise and Safe Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23071 - Contextual Causality with Large Language Models: A Survey Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22409 - F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19827 - When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24799 - Beyond Linear Context: Graph-Guided Evidence Navigation for Long-Novel Reasoning with a Local 9B Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22939 - To Consolidate or not to Consolidate? Evaluating the Impact of Consolidation in Multi-Reference Training using Peer Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22805 - Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23742 - Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23916 - Smoothed Analysis of Inconsistent A* Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.23680 - The Nelson-Nguyen Conjecture via Mean-to-Moments Concentration Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.22548 - Personalized and Trust-Aware Health Recommendation Policies for a Construction Workplace Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.12679 - Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22770 - MM-ContextFold: Context Folding for Multimodal Agentic Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research, JavaScript, React) URL: https://arxiv.org/abs/2609.23121 - IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.01590 - AdaMerge: Tuning-Free Patch Compression for Multi-Vector Visual Document Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.22562 - POI-Loc: A Fine-Grained POI Localization Benchmark and an Asymmetric Global-to-Local Matching Method Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02012 - MuSeR: Scalable Long-sequence Recommendation with Multi-interest Modeling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23677 - From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23853 - UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.11052 - From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23354 - PACE: Precise AI Cinematic Expression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19853 - Constraint Decay: The Fragility of LLM Agents in Backend Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI, Django, FastAPI, Python) URL: https://arxiv.org/abs/2605.06445 - Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18317 - Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21334 - On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21561 - Rethinking Multi-Agent Collaboration: When More Is Less Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19759 - Accelerating Dense LLMs via L0-regularized Mixture-of-Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21672 - Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21113 - Scaling Discovery through Test-Time Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21032 - A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21996 - Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27259 - OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21465 - Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21096 - dSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07151 - LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21492 - Verify, Don't Trust: Agentic Model Development for Video Discovery Retrieval at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21257 - High-probability guarantees for linear accessibility in feature superposition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09556 - Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21573 - AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21386 - Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08837 - Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13519 - Balance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30044 - Learning Cardiac Features: ECG Biometrics Across Time and~Exercise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21962 - How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27167 - A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19524 - Reducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21600 - GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21432 - 2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21511 - KnowDemo: Knowledge-Guided Robot Demonstration Generation from Human Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21229 - PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21493 - Attention-Aware Routing: Coupling Routing and Attention in MoEs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20974 - BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09134 - Modeling Human Behavior with Type Vectors Using AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18265 - Collab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03030 - Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07344 - Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21470 - ResNLS: An Improved Model for Stock Price Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.01020 - Fact Grounded Attention: Eliminating Hallucination in Large Language Models Through Attention Level Knowledge Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25252 - DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21423 - TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21139 - What Should We Ask Next? Retrieval-Aware Question Learning under Partial Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21924 - Runtime Authorization for Resources Acquired by AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14744 - LoRA Enhanced Contrastive Learning with SAS Vision Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21061 - Can Agents Design Better Chips with a Higher Level Abstraction? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21157 - Consistent Relexicalization of Clinical Documents using Graph-Based Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21387 - When Steering Fails in Latent Reasoning: A Latent-to-Language Transition Gap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21662 - AgenticRL: Agentic Reinforcement Learning with Self-Refinement for Complex UAV Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03963 - Deep Learning-Enhanced Real-Time Wi-Fi Sensing Through Single Transceiver Pair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02845 - CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18216 - Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13430 - Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.21683 - Physically Based Rendering in the Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21054 - AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21940 - The Impact of Semantic Pairs on Self-Supervised Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08722 - DiaVLo: Diagnosing Behaviours of Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22008 - MOSCOPT: Mixture-of-Skills Collective Optimization for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14399 - Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22086 - REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00271 - Git-Assistant: Planning-Based Support for Updating Git Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09224 - A Forced-Structure Reduction and Verifiable Bounds for Conway's 99-Graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11211 - Transferable knowledge graphs with executable learned operators for algorithm design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27922 - Beyond Final Answers: CRYSTAL Benchmark for Transparent Multimodal Reasoning Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13099 - Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10303 - TERMon: Detecting Persistent Behavioral Threats in Edge AI via Hardware-Native Ternary Runtime Monitor Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21713 - Do Personality-Tuned LLMs Make Better Social Agents? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21857 - CityLearn v3: A Configurable Simulation and Evaluation Framework for Realistic Control Studies of Renewable Energy Communities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21570 - AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21461 - Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16864 - SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21650 - World Modeling in Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21748 - Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12110 - Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21181 - Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21075 - WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31672 - The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01250 - Data-free On-policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14193 - Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21437 - BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07316 - Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21888 - SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21190 - Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18461 - One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21626 - EnSol: an environment-aware graph neural network for molecular solubility prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21151 - PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18120 - MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07036 - Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21971 - Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22067 - Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21743 - Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26088 - Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21208 - FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21228 - CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22068 - Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18366 - CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21686 - How Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21058 - SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21165 - Deep Reinforcement Learning with Buffered Quantile Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21327 - Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21149 - VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04355 - Ability-Residual Decoupled Modeling for Affective Cognitive Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21214 - A visual large language foundational model for medical image recognition using clinician-contributed online resources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06914 - NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21967 - The critical slowing down in training diffusion models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12597 - Representation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16775 - From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21117 - Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17605 - Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21486 - BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20886 - Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00226 - From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16344 - PlantShade: Predicting Plant Shadows for Lighting-Aware Robotic Agricultural Operation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21059 - Self-Explanation Tutor for Active Study of CS1 Worked Examples Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25180 - CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19818 - Calibrating Teacher--Student Discrepancy for On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21619 - A Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16923 - Understanding In-context Learning of Addition via Activation Subspaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.05145 - PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21263 - Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04287 - ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21755 - Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25364 - LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09384 - Self-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04277 - From Code Archival to Knowledge Graph: Bridging Software Heritage, COAR Notify and Wikidata Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21667 - PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00515 - Federated Deep Clustering Networks for High-Dimensional and Heterogeneous Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21829 - Dual-Interest Sequential Product Recommendation With Multi-Granular SSM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21548 - Large Language Models As Shannon Lossy Compressors Not Solomonoff Induction Estimators: The Singularity Is Not Near Without Symbolic Model Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05280 - RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20971 - Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08574 - Soda: An Object-Oriented Functional Language for Specifying Human-Centered Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.01961 - MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21811 - LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21325 - Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07799 - Outcome-Conditioned End-Effector Geometry Across Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21659 - VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21521 - WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21391 - Gricea: An Open Science Platform for Conversational AI Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22039 - Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21609 - Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21216 - ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18864 - A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21221 - Bio-MF: Low-Latency and High-Fidelity EEG-to-fNIRS Cross-Modal Generation for Hybrid Motor-Imagery Brain--Computer Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20904 - Learning-to-Optimize as the Missing Architectural Layer of AI-Native Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21519 - Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01240 - AutoRecLab: Describe the Experiment, Get the Code! Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21863 - Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21879 - Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21636 - An Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21805 - Diagnostic-Guided Longitudinal Modeling for Forecasting Retinal Atrophy Progression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16955 - Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21227 - How do LLMs Compute Verbal Confidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17839 - CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21722 - Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21401 - Visual Navigation Transformer with Pose Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21212 - GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21293 - Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21284 - Intent-Governed Tool Authorization for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22916 - GeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03869 - On the Limitations of Large Language Models for Conceptual Database Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11986 - EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21841 - Interference-Driven Clustered Optimisation for FM Spectrum Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21441 - Offline Multimodal Large Language Models for Decision Support in Air Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21390 - Auditing a KB Elicitation of Frontier LLM Knowledge: A Multi-dimensional Analysis of GPTKB v1.5 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07024 - Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01232 - Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12969 ## Community - Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/22/opus-and-sol-and-luna/ - llm 0.36 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/22/llm/ - Quoting @therealcornpop Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/22/therealcornpop/ - llm-anthropic 0.29 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/22/llm-anthropic/ - llm-typesafe 0.1a0 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/22/llm-typesafe/ - 150th airhacks tv: Spec-Driven BCE, BCE vs Hexagonal, Agent JFR, J2EE to Quarkus Source: adam-bien Topic: Java (+AI) URL: https://adambien.blog/roller/abien/entry/150th_airhacks_tv_spec_driven_bce_bce_vs_hexagonal_agent_ - boulodrome : LLM as proof assistant Source: ocaml-weekly-news Topic: OCaml (+AI) URL: https://alan.petitepomme.net/cwn/2026.09.22.html#8 - GPT-6 Sol (Max) Intelligence, Performance and Price Analysis Source: hacker-news Topic: General (+AI) URL: https://artificialanalysis.ai/models/gpt-6-sol - GPT-6 Sol and Luna Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/introducing-gpt-6-sol-and-luna/ - Claude Opus 5.5 Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/claude-opus-5-5 - Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why Source: hacker-news Topic: General (+AI) URL: https://ai-rete-rag.com/ - OpenAI is well positioned to fast-follow Jev Source: hacker-news Topic: General (+AI) URL: https://arcturus-labs.com/blog/2026/09/21/will-openai-eat-jevs-lunch/ - OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005 Source: hacker-news Topic: General (+AI) URL: https://www.cryptocellar.org/bgac/the-mvueh-break.html - People Training OpenAI's AI Fired for Using AI to Train the AI Source: hacker-news Topic: General (+AI) URL: https://www.404media.co/people-training-openais-ai-fired-for-using-ai-to-train-the-ai/ - Did OpenAI solve the wrong Navier-Stokes problem? Source: lobsters Topic: General (+AI) URL: https://www.scientificamerican.com/article/did-openai-solve-the-wrong-navier-stokes-problem/ - Show HN: JevBench, a reproducible benchmark for typed decision models Source: hacker-news Topic: General (+AI) URL: https://benchmarkheaven.com/jev-models - Jev introduces a new shape of LLM Source: hacker-news Topic: General (+AI) URL: https://simonwillison.net/2026/Sep/21/jev/ ## Media - Vibe coding in the pit lane 🏁 Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/SGODy6sZKCc