TILens Daily Edition 2026-09-25 Filters: topic=ai, github=hidden Stats: 750 articles, 25 sources, 698 research papers Top topics: AI, AI Research, Information Retrieval ## News - Proaction boosts sales 60% and saves 75+ hours with Codex Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/proaction - Amazon EC2 M8i and M8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-ec2-m8i-m8i-flex-thf/ - Amazon EC2 R8i and R8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/ec2-r8i-r8i-flex-thf/ - Amazon EC2 C8i and C8i-flex instances are now available in additional regions Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/09/c8i-c8i-flex-thf-september-2026/ - Spring AI 2.1.0-M1 Available Now Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/09/25/spring-ai-2-1-0-M1-available-now - Wayfair boosts catalog accuracy and support speed with OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/wayfair - Everything That Happened in AI This Weekend So Far (Friday, September 25, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-this-weekend-so-far-friday-september-25-2026/ - Context Over MCP: Part V The Form Is the Tool. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/wolfejam/context-over-mcp-part-v-the-form-is-the-tool-1cad - AI 2040 Plan A: What It Predicts and How the World Gets There Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/ai-2040-plan-a-predictions-path-to-superintelligence/ - Unsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/unsecured-openai-agents-posted-53-user-images-on-the-internet-without-the-labs-knowledge/ - Court rules Pentagon can blacklist Anthropic for refusing to enable Claude features Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/tech-policy/2026/09/court-rules-trump-can-blacklist-anthropic-for-refusing-to-enable-claude-features/ - Anthropic to pay Akamai $11.6 billion over seven years in cloud deal Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/anthropic-to-pay-akamai-11-6-billion-over-seven-years-in-cloud-deal/ - What We Missed: Google Gemini Joins the AI Escape Party Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyber-risk/what-we-missed-google-gemini-ai-escape-party - Meta’s AI Tamagotchi bet is…working? Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/video/will-metas-ai-tamagotchi-bet-isworking/ - For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/for-months-openais-agent-swarms-have-been-attacking-online-databases-to-find-obscure-facts/ - Anthropic’s founders seek voting control ahead of IPO Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/25/anthropics-founders-seek-voting-control-ahead-of-ipo/ - A summary from the 2026 Git Contributors' Summit Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1096819/ - LLM Streaming with Embabel Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/llm-streaming-with-embabel.html - Running an Autonomous AI Agent Stack on Android with Termux — No Cloud, Just a Phone Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/sam_hiotis_117598dbfa3ac2/running-an-autonomous-ai-agent-stack-on-android-with-termux-no-cloud-just-a-phone-33dk - The pattern: Decoupling marketing copy from React components Source: devto-javascript Topic: JavaScript (+AI, PostgreSQL, React) URL: https://dev.to/pavan_s_poojary/the-pattern-decoupling-marketing-copy-from-react-components-5ain - The Next Big AI Model Can't Write a Single Sentence Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/renishb10/the-next-big-ai-model-cant-write-a-single-sentence-551p - React PDF bbox Highlighting: Show RAG Citations on the Page Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/fangtanbamrung/react-pdf-bbox-highlighting-show-rag-citations-on-the-page-il9 - Asahi fork embraces LLMs and lands Linux on the M4 Mac mini Source: theregister Topic: General (+AI) URL: https://www.theregister.com/os-platforms/2026/09/25/asahi-fork-embraces-llms-and-lands-linux-on-the-m4-mac-mini/5298931 - OpenAI and Cursor agree on agent coordinators. They disagree on who runs them. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-cursor-coordinator-agents/ - Claude Spotted a DNA Pattern Scientists Had Overlooked Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-dna-pattern-enzyme-discovery/ - Meta's Connect turns into a Muse takeover Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/meta-connect-turns-into-a-muse-takeover - Spring AI RAG Tutorial with Spring Boot Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/spring-ai-rag-tutorial-with-spring-boot.html - 😺 Meta unveiled Muse Charm, a pocket AI Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-unveiled-muse-charm-a-pocket-ai/ - The Pentagon wants $30 million to build an AI-powered lie detector Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/25/1145144/pentagon-ai-lie-detector/ - A Guide to Structured Output in Spring AI Source: baeldung Topic: Java (+AI) URL: https://www.baeldung.com/spring-ai-structured-output - Everything That Happened in AI Today (Thursday, September 24, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-thursday-september-24-2026/ - Claude Opus 5.5 Broke Our GPT-6 Benchmark: Full Livestream Guide with Demos, Prompts & Timestamps Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/claude-opus-5-5-vs-gpt-6-sol-demos-prompts-timestamps/ ## Research - 10 Things I’m Learning Beyond AI to Become More Technologically Fluent Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/10-things-im-learning-beyond-ai-to-become-more-technologically-fluent/ - Your Model's MSE Is Lying to You: Part II Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/your-models-mse-is-lying-to-you-part-ii/ - RAG Isn't an Agent — I Built the Layer Between Retrieval and Action Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/rag-isnt-an-agent-i-built-the-layer-between-retrieval-and-action/ - Jev vs. LLMs: When AI Moves from Generation to Decision-Making Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/jev-vs-llms-when-ai-moves-from-generation-to-decision-making/ - Stochastic Inertial Krasnosel'skii-Mann Iteration Achieves Near-Optimal Sample Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28543 - Neural Transport Nested Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29413 - CFD Correction of Open Tip Clearance Flow in a Compressor Cascade Using VAE Latent Space Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28558 - TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18407 - Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29945 - Rufus-Air: An Open LLM Post-Training Recipe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29421 - Hybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28491 - Do Audio Language Models Hear and Read Distinctive Features Alike? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30167 - Revalidation Beats Stateful Routing for Scientific Surrogates Under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29715 - Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08329 - Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29027 - PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29578 - Physics and Data Driven Transformer-Mamba Framework for Flow Field Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29087 - Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29867 - Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29711 - 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 - Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09211 - TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05145 - Every Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23393 - RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28850 - SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28582 - Complete Neural Electronic Initialization Accelerates Materials DFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21759 - An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29696 - Certified Task-Conditioned Active Observability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28520 - Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28722 - Improving global precipitation forecasts with an AI weather model trained on satellite observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03210 - RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23012 - Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28107 - J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26582 - CatSIM: A Categorical Image Similarity Metric Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2004.09073 - A JoLT for the KV cache: Near-Lossless KV Cache Compression via Joint Rank-bit Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12550 - Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29317 - Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28604 - How Weight Encoding Affects Language Model Placement and Performance on the Apple Neural Engine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22110 - Minimally Invasive Steering of Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30218 - SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28553 - Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29307 - Learning from Mixed-Quality Deployment Experience for Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29000 - Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.18929 - Edge AI on Constrained Devices for Binary Sleep-Wake Classification in Dynamic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29163 - Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04317 - Technical Manual for Toolkit for Confidence-Corpus Consistency via Fine-Tuning on a Fabricated Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28747 - SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29050 - Auditing Bayesian Graph Alignment: Diagnostic Comparisons and Reference Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23232 - Agentic Detection of Online Conspiracies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30250 - Three Ways Classical Test Theory Misleads for LLM Judges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29709 - MF-SCBO : Multi-fidelity Scalable Constrained Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29941 - Multiscale Reward Hedging from Correct Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06825 - Machine Unlearning for Gibbs Supervised Learning Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29409 - GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30147 - An Order-Theoretic Characterization of Consistent Inductive Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28551 - A Multi-level Information Integration Framework for Physically Verifiable Fault Diagnosis of Rotating Machinery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22797 - Gradient Networks for Universal Magnetic Modeling of Synchronous Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14947 - FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29812 - Invertible Query-Key Coupling Composes with Attention Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01683 - HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Mesh Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28601 - On the second-order optimization for spiking neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29379 - A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29630 - Learning Causal Structure of Time Series using Best Order Score Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05370 - DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28570 - LabFactory: Building and Evaluating Executable AI Labs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28697 - Policy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28737 - Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28718 - RADAR: Readiness for AI Discovery and Agentic Reach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28480 - Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29405 - BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29069 - Robust Detection of LLM-Generated Text under Contamination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29935 - NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28587 - Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28749 - Aftab: A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07335 - PoEM: Predicting RL Outcomes from Existing Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30226 - The Mechanics of Delta Learning: Target Design for Generalizable Scientific Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28782 - Orbital Error Dynamics: Self-Organized Criticality, Ephemeral Parameter Resonance, and Non-Linear Biological Ontologies in Zero-Storage Neural Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30115 - TopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29740 - Stream Recursion Model (SRM) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28809 - Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02986 - RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24972 - Beyond Pairwise Attention: Higher-Order Modular Attention for Efficient Sequence Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11133 - When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29580 - Learning to Discover Interesting Mathematics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28603 - Sufficiently Reduced Distributional Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29291 - Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29706 - From Processing to Functionality: Engineering Accessible Material States in Cu-Embedded SiO$_x$ Memristive Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30047 - SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29446 - Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30198 - Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28974 - fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28607 - When Does Unsupervised Learning Succeed or Fail? A PoS Perspective on Reconstruction-Based Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28832 - An Analytical Theory of Auxiliary Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29774 - CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29807 - Classifier-Dependent Benefits of Pseudo-Labeling for Semi-Supervised Android Malware Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29564 - Path-specific harm decomposition: A partial identification framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29938 - Spectral-Guided Diffusion: Accelerating Inference via Static Spectral Layer Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29505 - CARE: Condition-Aware Representation Regularization for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28561 - MORE-PLR: multi-output regression employed for partial label ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29386 - REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19903 - Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28838 - Learning to Fluctuate: Statistical Foundations for Causal Tabular Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26290 - NS-ATTENTION: Newton-Schulz Transformations of Attention Outputs in Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27735 - On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29755 - A hybrid analytical-PINN model for subsurface simulation of geothermal heat exchangers in heterogeneous underground Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12271 - GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29999 - Enabling Approximate Joint Sampling in Diffusion LMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22738 - Functional dynamic mode decomposition: Learning infinite-dimensional systems from data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29159 - Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30150 - Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29382 - Calpric: Inclusive and Fine-grain Labeling of Privacy Policies with Crowdsourcing and Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2008.02954 - Automatic Harness Evolution for Hardware Design Verification: Can LLMs Consolidate Gains Across Discovered Harnesses? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28908 - An Exploratory Ablation of a Small MLA--SSM Hybrid Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29618 - Certified Predictive Value-of-Advice Gating for Cost-Aware Language-Model Guidance in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29548 - CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29518 - Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29931 - Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28567 - SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28563 - Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18366 - RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28625 - The Sharp Tail of Uniform Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24098 - DeGRe: Dense-supervised Generative Reranking for Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25749 - An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28528 - Does a model's stated reason for rejecting a candidate do any work? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30151 - Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29636 - A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29584 - Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29453 - Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30036 - SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18290 - A New Gap Sequence for Shellsort: RL-Driven Algorithm Discovery Beyond $N^{4/3}$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29881 - QUARTET: Quad-branch cross-Attention and Random-walk Traces for Enhancing Transformers on Relational Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26855 - Intrinsic-Extrinsic Coupling in Learning Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30185 - Foundations of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.09223 - A Concentration Bound for Two-Timescale Actor-Critic Algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29117 - DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20052 - From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29283 - Dynamic Generalized Gromov-Wasserstein Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20008 - No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23667 - Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17965 - Learning tactile perception from high-bandwidth single-point sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24621 - Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28670 - GBFRVFL: Granular-Ball Computing-Based Fuzzy Random Vector Functional Link Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29670 - GridSFM: A Foundation Model for Solving AC Optimal Power Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30173 - Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29866 - Federated Learning of AnDE Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28695 - Quantum Attention by Overlap Interference: Predicting Classical and Many-Body Quantum Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06699 - GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29327 - AIR: Analytic Imbalance Rectifier for Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.10349 - Task-Resolved Fisher Spectroscopy for Quantum Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29570 - Diffusion-aided Task-oriented Semantic Communications with Model Inversion Attack Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19886 - Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29906 - How Many Humans Are 32 LLM Judges Worth? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21277 - Time-Series Foundation Models That Understand Data Revisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28576 - Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27166 - Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29988 - Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29095 - Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15257 - Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28935 - GeoDose-CP: Graph-Local Conformal Inference for Continuous-Treatment Earth Observation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28895 - Online Task Adaptation via Self-Organisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29281 - Learning and interpreting policies for simultaneous entanglement requests in quantum networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30157 - Direct Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29466 - Time-Varying Bayesian Optimization Without a Metronome Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.18963 - Learning a Flow to Self-Supervised Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29350 - TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28590 - A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13343 - Predicting Symptoms of Amotivation and Anhedonia among University Students with a Novel Oversampling Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29690 - When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29937 - EvoTreeNAD: Genealogy-Guided Evolution for LLM-Driven Neural Architecture Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29016 - ASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29191 - Elucidating the Conformal Structure of the Brinkman Penalisation Method for Geometry-Adapted, Structure-Preserving Operator Learning of Hamiltonian PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29847 - Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29508 - A Multimodal 3D Foundation Model for Light Sheet Fluorescence Microscopy Enables Few-Shot Segmentation, Classification, and Deblurring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26026 - DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.08875 - Sample-Weighted End-to-End Trace-Norm Geometry for Multitask Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29520 - VG-TIE: An interpretable tabular-to-image encoding method based on visibility graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29650 - Speculative Evaluation of Stochastic LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28560 - FlowAtom: Atom-Based Evidence Aggregation for Multi-Label Website Fingerprinting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29330 - Beyond Average Safety: Chance-Constrained LLM Fine-tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29960 - On Cost-Aware Designs for Sequential Hypothesis Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.19067 - IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07709 - Named Entity Recognition using Sliding Window Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29682 - Learning Generalizable Behaviors for Terminal Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22631 - Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22170 - UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28610 - Continuous Online Fault Detection for Mobile Robots via Adaptive Edge Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29194 - MLPerf Automotive Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.27065 - Generalized Graph Variational Autoencoders: Bounded Divergences Control Posterior Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29546 - MQSS-Selector: RL-Guided Pass Selection for an MLIR Compilation Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30104 - Efficient Continuous DEM Reconstruction under Limited Target-Resolution Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29864 - Return or Revise? Learning When Revision Helps Retrieval-Augmented QA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30087 - Few-Shot Specific Emitter Identification via Integrated Complex Variational Mode Decomposition and Spatial Attention Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16786 - Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02829 - Learnable Time-Frequency Masks for Explaining Time-Series Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29270 - Two Dimensions Govern Agnostic Multiclass Transductive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25326 - CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14171 - Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17556 - A Rapid Pipeline for Training and Deploying ML Models on WeBe Band Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29084 - A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30215 - FB-GDM: Fully-Bayesian Guided Diffusion Models for High-Dimensional Linear Inverse Problems via Unsupervised Variational Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29216 - Unmasking Shortcut Learning in IoT Intrusion Detection: A Forensic, Multi-Paradigm Evaluation of Feature Dependence and Data Leakage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28725 - Multi-Dimensional Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29958 - Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28876 - The Alignment Illusion in Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30210 - Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28860 - LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01754 - TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19613 - Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28716 - Physics-Guided Multi-Objective Deep Learning for Ultrasound RF Data Interpolation in Resource-Constrained Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28775 - TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11700 - KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30059 - Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29142 - Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18574 - CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20025 - Paging the Experts: A Reproducible Characterization of Flash-Backed MoE Inference on iPhone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29032 - An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14892 - Evidence-Driven Differential Diagnosis of Malignant Melanoma Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29613 - Algebraic Expressivity Certificates for Shallow Polynomial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28500 - Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29499 - Graph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29668 - Pointwise Generalization in Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18598 - DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29092 - Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28578 - The Fellowship of the Query: Learning Retrieval Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28653 - Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28793 - DiffUNet^2: Bidirectional Conditional Diffusion for Probabilistic Scientific Spatiotemporal Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03926 - Stable and Faithful Explanations for Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28502 - Optimal Recovery Meets Bayesian Learning: Where Worst-Case Bounds Pay Off Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29622 - Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28578 - To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30227 - ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27532 - SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29814 - AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30088 - PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08101 - CaliPPer: quantifying, predicting and improving AI model performance for binding prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07258 - Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30258 - 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 - When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28870 - Who Owns the AI Recommendation? A Multi-Industry Empirical Map of Brand Category Ownership Across Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23057 - WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29772 - Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29101 - Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29600 - BRFID: Toward Byzantine-Robust Federated Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28599 - Residual Correlation as a Diagnostic for Joint-Uncertainty Gains from GP Coregionalisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30085 - A Probabilistic Approach for Model Alignment with Human Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.10771 - Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29024 - Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31046 - Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29001 - ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29398 - LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28086 - Limited Structural Reliability in Public Educational Prediction Benchmarks: A Four-Dimension Audit of Seven Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29625 - When Explanations Cannot Be Read: Measuring and Correcting SHAP and LIME Rendering for Right-to-Left Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28565 - Precise Convergence Speed of Clipped SGD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29458 - The Sequential Price of Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29674 - Transformers as Cross-Task Learners: Shared Structure Drives Sample Efficiency in In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29060 - Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29648 - AFT Neural Function Approximators for 1D Nonlinear Force Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29242 - Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28564 - From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28477 - TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29733 - TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29099 - Lightweight Probabilistic Downscaling from a Deterministic Base Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29383 - Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06130 - Not All Synthetic Data Are Equal: Expert-Committee Audit Screening for Imbalanced Crash-Injury-Severity Prediction in Automated Driving Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29687 - Matrix Aggregation Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28562 - A Corpus of Real Scam- and Spam-Call Conversations from an Active Voice-Agent Honeypot Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29528 - Spectral Graph Neural Networks with Hermite Polynomials: A Comprehensive Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28979 - Selective Inference for Deep Clustering in Latent Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28756 - Cost-Sensitive Online Window Size Selection for Portfolio Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29887 - Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30212 - ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29102 - A Contraction Framework for Stochastic Operators with Bootstrapping: Application to TD Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29961 - How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30074 - AERIAL: Adversarial Evaluation of Robustness in Accuracy-Preserving Low-Precision EEG Decoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30037 - RAPTOR: RAndom-projection Physics-informed Transient sOlveR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29714 - Lossless Anti-Distillation Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18829 - Reward Hacking Challenges Oversight of Autonomous Research Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28614 - Unraveling the cognitive patterns of Large Language Models through module communities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.18192 - A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18279 - MemGuard-Alpha: Limits of Membership Inference for Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26797 - Diverse Geometries, Frozen Weights: Robust Heterogeneous Treatment-Effect Estimation via Causal Expert Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29974 - Tracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29951 - RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29403 - Exploiting answer-invariant redundancies in satellite imagery for efficient VLM inference on edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29029 - Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29096 - Multimodal AI predicts clinical outcomes of drug combinations from preclinical data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.02781 - Towards Deployable Underwater Vessel Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29179 - Open-access model for detecting openly dumped dispersed municipal solid waste from crowdsourced UAV imagery in Sub-Saharan Africa Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02316 - A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06607 - M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28836 - Nuclear Norm-Regularized Bayesian Matrix Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30078 - Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19084 - Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29048 - Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30017 - TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29633 - Feature Space Selection and Heterogeneous Effect Estimation for Blood-Brain Barrier Permeability: A Random Forest to the Generalized Random Forest Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29076 - The kernel of graph indices for vector search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20584 - Sequential Confidence Sets for Coverage-Constrained Conformal Model Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28522 - MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10287 - Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2603.10044 - Self-Localizing MIMO Beam Mapping with Continuously Evolving Channel Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17007 - Personalised federated learning for Riemannian and Euclidean EEG decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29037 - Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.17044 - Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29694 - BLADE: Distilled LLM Regularization for Calibrated Knowledge Graph Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29487 - LastOPD: Taming Collapse in Latent On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28845 - Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30079 - GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15723 - Reconstructing short-lived particles using hypergraph representation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.10149 - The Impossible Trinity of Time-Series Validation: A Conservation Law among Training Sufficiency, Test Coverage, and Temporal Causality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29530 - Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28581 - CrossSafe: Towards Cross-Embodiment Latent Safety Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28984 - A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01028 - BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29268 - Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26865 - Image Fidelity is Not Field Fidelity: Joint Thermodynamic Reconstruction and Error Localization in Neural Tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28868 - Transductive Off-policy Proximal Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.03894 - M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28684 - TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29322 - UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28605 - Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24726 - A Particle-Swarm-Assisted Gradient Meta-Learning Algorithm for Joint Transmit Precoding and STAR-RIS Coefficient Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29150 - Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13422 - Concurrent Split Learning Through Stable Client Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29395 - OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28665 - From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29879 - Not All Confusion Is Equal: A Source-Aware Uncertainty Diagnosis for Fine-Grained Aircraft Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29959 - On the SoS Certifiability of Log-Concave Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30105 - Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28682 - Automatic Rank Allocation for Low-Rank Adaptation in Large Language Models via lp Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28998 - Common Covariance Geometry and Certification for Brownian Kernel Ladders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29525 - Post-Training Leaves Behavioral Shadows on Unrelated Decisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29233 - Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28792 - Why Does Misinformation Propagate Faster? An Algorithmic Perspective on X Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28947 - Learning the Cost of Reliable Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28322 - OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28589 - An Empirical Study of VLM Pipelines for Long-Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29933 - SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29803 - Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.30001 - SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29721 - Claim-Gated Source-Risk Auditing for Generative Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29145 - Fair Feed Ranking for Participatory Budgeting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29819 - Measuring Brand and Source Discovery under Repeated LLM Queries: A Finite-Sample Audit Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05059 - Learning Better Reasoning for Generative Recommendation with Semantic IDs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29973 - SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.14277 - Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29282 - OBLIQ-IR: Training a Dense Retriever for Oblique Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29649 - X-Rec Technical Report Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29180 - Seek: Self-Evaluative Exploration for Knowledge Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28980 - CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29474 - EvLink: Source-Grounded Evidence Linking for Graph RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29695 - WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2507.00938 - SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29652 - From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29983 - C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29735 - Cross-Country Code-Mixing for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28972 - Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29609 - Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AI Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29703 - LSF-SR: Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29815 - Ingest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29661 - Reinforcement Learning with Verifiable Rewards for Small Search Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.28765 - ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29182 - A Systematic Multi-Domain Evaluation of Document Retrievers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.29455 - A Tight Analysis of Khatri-Rao Oblivious Subspace Embeddings Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2608.28094 - Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14815 - Parts-of-Speech as Emergent Categories in SAE Latent Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29362 - The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28479 - An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28703 - Tag-Aware Structured Text Translation: Towards a Systematic Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29131 - Recovering the Zipfian Distribution in Unsupervised Term Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10781 - What, When, and How: Audio Description as Constrained Global Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30121 - Learning to Ideate for Scientific Impact Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29802 - BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29371 - A Group-Based Resource Allocation Model for the Fractional Knapsack Problem Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06470 - Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29479 - A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30160 - JEV vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29769 - JevOut: Natural Context Can Flip Decision Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30243 - Interactive In-Meeting Speaker Correction with Human Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.18377 - PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30094 - STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29607 - Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04452 - VietPrism: A large-scale Vietnamese speech and deepfake corpus with diverse dialects and code-switching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30005 - Artificial Societies Benchmark: A Validation Framework for Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30030 - agentic-ger: terminology recovery in long-form speech using global context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29428 - Language Specific Knowledge: Do Models Know Better in X than in English? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14990 - ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30199 - Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00949 - IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29444 - Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26618 - Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29848 - Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18395 - TimeBraid: Unifying Time Series and Language for Understanding and Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29792 - SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27717 - LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15397 - Confident but Wrong: A Constrained Decoding Diagnostic for Low-Resource Automatic Post-Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29680 - Evaluating Explanation-Driven Vision-Language Reasoning via Generation Order Interventions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29496 - DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12872 - Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25404 - An Empirical Study of Automating Agent Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11378 - How To Do Things With Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29657 - Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29410 - Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29798 - Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29056 - ModularSQL: A Runtime Guardrail for the Multiplicity Blind Spot in Text-to-SQL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29573 - From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29370 - Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29251 - 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 - CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24312 - No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29245 - SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30238 - BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28758 - EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29511 - Universal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25498 - Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29429 - Conduct Under Pressure: What Sixty Language Models Do When a User Pushes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25447 - Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29855 - Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17360 - Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28778 - Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08064 - Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28713 - iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29626 - StepCOPS: Closed-Testing Lower-Tail Certificates for Language-Model Policy Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29549 - Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29509 - PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29718 - Benchmarking Arabic--Russian Machine Translation: A Comparison of Fine-tuned NMT and Few-shot LLMs under Rich Morphology and Low Lexical Overlap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29559 - Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27650 - DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18612 - Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29845 - When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28475 - Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30009 - CRISS: A Retrieval-Augmented AI Chatbot for Assisting Cancer Registrars Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29075 - A Native-Reference Phone-Class Geometry for Second-Language Pronunciation Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30075 - Combating Instruction Conflict via Energy-Driven Latent Conflict Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08646 - Polite but Misaligned: Evaluating LLM Politeness Judgments Against Human Pragmatic Norms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29001 - Temporal Taxation Compounds Under Post-Training Compression of Whisper Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28739 - Multimodal Thinking with Renderable Programs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30130 - Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28487 - Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27690 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29146 - How Do Users Negotiate Harmful Value Conflicts with AI Companions? A Study with Minion, a Technology Probe for In-Situ Human-AI Conflict Response Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.07042 - Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28854 - PUBG Ally: A Conversational Embodied Agent as an AI Teammate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29837 - ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29349 - Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29800 - Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14121 - IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06676 - When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25832 - Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18744 - EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29230 - Small yet Assistive: Spatially-Aware Post-Training for Low Vision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28757 - Conversational DNA: A Visual Language and Interactive Atlas of Human and AI Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07520 - Evaluation of OpenAI o1: Opportunities and Challenges of AGI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.18486 - Controlling Backchannels in Streamable Full-duplex Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29418 - LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04489 - Persona Prompting in Multimodal Urban Perception: Descriptive Convergence and Interpretive Variation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29064 - Frontier Lag: A Bibliometric Audit of Capability Misrepresentation in Academic AI Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04135 - RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04457 - PROOF: Profiling Reliability of Object-Level Facts in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29504 - PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28727 - Grammatical "grandmother neurons" are rare in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29328 - Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30012 - Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29601 - What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29507 - COILD: An Indic-Centric Parallel Corpus and Benchmark for Machine Translation Across Indian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28826 - Can Classical Semantic-Extractive Summarization Be Evaluated in Hindi? A Replication Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29090 - LLMersion: A Local-First AI Agent Framework for Low-Cost Home Language Learning toward Educational Equity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29672 - ChunkRank: Model-Aware Text Chunking and Abstention-Aware Answer Selection for LLM Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29828 - MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29913 - Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28988 - LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27220 - pylazaro: a Python package for anglicism extraction in Spanish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29276 - How broad is that claim? Mapping Generalisation in NLP Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14770 - Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29183 - Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25176 - Two Emojis of Difference: What Multilingual Affective Generation Benchmarks Actually Measure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29445 - LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07746 - Scoring Both Directions: LLMs realize the MRS they cannot reliably parse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30071 - Script Choice in LLMs: Evidence for Late-Layer Commitment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28784 - Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28673 - Human Agreement and Return Association Are Not Interchangeable Criteria Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11144 - Reasoning Instructions Can Break Answer Decoding in Vision--Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29278 - MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.14948 - An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21424 - Learning New Words from Unlabeled Test Data in Automatic Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28877 - DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29684 - ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30184 - Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29397 - Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30137 - YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29448 - Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30048 - Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29123 - R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30100 - MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29015 - Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29043 - Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.29952 - Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29494 - Likelihood Ranking doesn't Scale Like Prompting in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29390 - Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29928 - Self-Play Pretraining with Zero Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30063 - Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29333 - Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19625 - PAWS: Policy-driven Agentic World Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28547 - Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26758 - The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11489 - Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28879 - Cryptographically verifiable authorization for autonomous AI agents: a falsifiable hypothesis and proof of concept Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21325 - The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29045 - The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15494 - Training Object Permanence in World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28654 - 3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07907 - A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29154 - Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29851 - Fair Like Us? Auditing LLM Alignment in Resource Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29692 - Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29140 - WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29372 - VLANeXt: Recipes for Building Strong VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18532 - QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29592 - A Living Benchmark for Information Retrieval from Electronic Health Records Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30205 - Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29995 - DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28796 - Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29697 - Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29892 - TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03699 - Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28991 - Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17174 - Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28963 - Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11433 - Human-AI-Powered Hypothesis Testing: Cost-Aware Selective AI Scoring and Sequential Human Escalation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28859 - Rolling-WAM: World Action Models with Rolling Imagination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30247 - A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29874 - Neural-Network Solutions to Real-Space Charge Density and Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14906 - NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03159 - Right Choice of Classification Algorithms Based on Reinforcement Learning for Prediction of Non-Alcoholic Fatty Liver Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29181 - Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30219 - PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29599 - The Gold in Bias: Maturing the AI Design Process through Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29730 - ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29948 - AgileLog: A Forkable Shared Log for Agents on Data Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14590 - Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26176 - AgentKernel: The Trust-Native Agentic Operating System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29647 - Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29876 - Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29358 - SheetMind: Actions Set Accuracy, Agents Set the Failure Mode Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12339 - Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29363 - Accelerating Video Diffusion via Training-Free Trajectory Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30096 - Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14047 - ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.16763 - Working with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29901 - DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29309 - Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11351 - Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28559 - On the Effectiveness of Kernel-Level Evidence for Agent Security Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28915 - BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28557 - From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29051 - Progressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28693 - Hyperbolic Multimodal Continual Learning: A Closest-Admissible Solution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29329 - A General Framework for Budgeted Threshold Incentives on Request Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29724 - ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29269 - CounterRoute: Self-Routed Reasoning via Hierarchical Counterfactual Credit Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29109 - Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29808 - EnigmaForge: The Question Is Hidden in the Story Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30144 - AI in Science: Early Insights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28504 - CoSWA-YOLOv12: Scale-Invariant Tiny Object Detection and Segmentation of Malaria Parasites Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29527 - SkinAgent AI: A Safety-Grounded Multimodal Agentic Framework for Non-Diagnostic Skincare Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29341 - Towards An LLM-Driven Unified Conversion Framework for BT and FSM in Autonomous Intelligent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29228 - TWIST: A Proposed Benchmark for Intervention Quality in Conversational Memory, with a Human-Validated Draft-Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28575 - Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30214 - Answering Path Queries under Linear and Guarded Existential Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22636 - Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29366 - ERRAND: Budgeted Maintenance of Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29545 - Band-Attention Modulation Network for Robust Face Forgery Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.06022 - When No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29312 - JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14777 - From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28942 - KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28761 - Cross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29556 - Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28613 - World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29964 - Is Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29560 - Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28572 - Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28609 - Deep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05998 - Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30217 - HEXIS: Compiling Skills into Extended Finite State Machines Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30123 - Less is More: Encoder-only Audio-Visual Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29121 - 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 - Detecting Glaucoma Across Multi-ethnic Myopic and Non-Myopic Populations Using an Uncertainty-Aware Vision Transformer: A Multicentre Model Development and Validation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29433 - AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30264 - AgriCountDINO: Parameter-Efficient Exemplar-Guided Counting and Localization in Agriculture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29460 - MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04756 - Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26990 - RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29490 - When Does Action Credit Need Updating? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29007 - Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29587 - Segment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29384 - Agent Memory with Episodic Retrieval for Financial Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28771 - Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29775 - Jev-Mobile: Jev as an Executor for Mobile GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30186 - Dual-Frontier: When Can an Agent Trust Its World Model? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26293 - Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26760 - Do World Models Make Better Robots? A Survey of Evaluation Benchmarks for Predictive Embodied Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29669 - SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30054 - AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29014 - Learned Cross-Task Relationships in Multi-Task Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28776 - Long-horizon autoformalization of a core theorem underlying MIP* = RE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19814 - SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29235 - Neuro-symbolic AI for Industrial Configuration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29947 - Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30027 - Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28910 - LLM Agents Can Easily Tamper With Their Own Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30266 - S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29813 - Multi-Agent Orchestration of 3GPP Channel Estimators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29044 - Pistis Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28554 - Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29396 - BEHAVE: Real-Time Modeling of Human Systems as Observable Complex Dynamical Systems and Operational Objects for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12730 - Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28843 - Functional Architecture of European Electricity Trading Markets: Requirements for AI Supported Trading Systems under Regulatory Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29108 - ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29963 - Can Labor Markets Function in the Age of AI? The Evaluation Bottleneck in Hiring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30058 - SHINE: Sequential Hierarchical Integration Network for EEG and MEG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23960 - 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 - The Last Human Gate: Forward Deployed Engineering for Governance Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29345 - CATCH: Counterfactual Anatomical Tissue Inpainting with Conditional Haar Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29591 - SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29465 - AI-Moderated Interviews for Market Research and Digital Twins Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29143 - Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29266 - Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01810 - HarnessPAI: An Evolving Harness for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29166 - Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21980 - Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.30177 - ReCalMatch:Reliability-Calibrated Semantic Guidance for Semi-Supervised Fine-Grained Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29678 - Coding Agents for Generalized Task and Motion Planning Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30233 - Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29781 - Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29912 - Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20470 - Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29522 - MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03710 - Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29744 - When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29875 - Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31825 - When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29547 - When Honesty is Not Enough in AI Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29189 - SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27621 - Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24423 - Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18640 - Investigating White Blood Cells as a Source of False-Positive Malaria Parasite Detection in African Blood-Smear Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29663 - Math Reasoning in LLMs is Organized by Approach, Not Topic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27041 - TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29240 - Safe Skill Retirement for Physical Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29543 - WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29106 - Anatomy-aware cross-speaker adaptation of complete vocal-tract acoustic-to-articulatory inversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29766 - UNWIND: Any-Length Facial Video for Stress Detection without Temporal Windowing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29553 - A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00322 - Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29169 - Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29940 - RAPID: Robot Agentic Programming from Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30249 - The Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29187 - CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28524 - Decoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29820 - Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29144 - SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30192 - TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15594 - TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30222 - Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30055 - Driving Epidemic Models with AI Agents: the Epydemix Agent Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28692 - Frame-to-Panorama Localization and Context-Aware Sampling for Scene-Specific Ship Detection in a Smart Marina Testbed Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29447 - Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29156 - Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29773 - GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29541 - TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29264 - EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29064 - SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04119 - Chart-Supported or Model-Supplied? Examining MLLM-Generated Claims for Accessible Visualization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25021 - How does Adversarial Influence Scale in Multi-Agent Systems? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30028 - MorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29908 - Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28585 - NNV3: Expanding Neural Network Verification to New Architectures and Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30050 - BiGraph-Diffuse: A Bidirectional Diffusion Language Model with Graph-Structured Retrieval For Mental Health Counseling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29519 - An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29381 - Control the Harness, Control the Cost: Routing and Governing AI Coding Agents in the Enterprise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28919 - Generative Evolutionary Design of Voxel-Based Soft Robots with Provable Optimality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29491 - Who Holds the Pen? Let Specifications, Not Agents, Sign Off Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29921 - Beyond Surface Style: Aligning Multi-Turn User Simulators with Behavioral Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28690 - KeyGen: Unsupervised Keypoint based Object-Centric Representations for Category-Level Policy Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28818 - AI-based detection of worsening heart failure from low-resolution telemonitoring data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29742 - Clinical Knowledge Graphs for Chest X-Ray Device Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29536 - GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20455 - To Think or Not to Think: Allocating Reasoning Where It Helps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29664 - PFArena: Benchmarking Language Models for Protein Modification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28921 - Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28940 - TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28506 - A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28806 - IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29167 - HiPACE: Hierarchical Phase-Boundary Analysis and Controlled Evaluation of Feature Absorption in Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29551 - Cross-Task Generalization in Handwriting-Based Alzheimer's Screening via Vision Language Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.05841 - Deep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29256 ## Community - Quoting John Gruber Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/25/john-gruber/ - Northern Gannet, Great Blue Heron, California Brown Pelican Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/25/sighting-403293902/ - OpenAI’s Systems Went Rogue and Meddled With U.S. Government Websites Source: hacker-news Topic: General (+AI) URL: https://www.nytimes.com/2026/09/25/technology/openais-ai-us-government-websites.html - Tell HN: Codex Is Down [fixed] Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49851032 - Show HN: Recurse – Develop and deploy specialist agents faster Source: hacker-news Topic: General (+AI) URL: https://recurse.run - Show HN: Ekselio – Loveable for finance workflows (local first) Source: hacker-news Topic: General (+AI, JavaScript, React) URL: https://www.gptbeyond.com/try?home=1 - Revealing the details of how OpenAI agents hacked Hugging Face Source: hacker-news Topic: General (+AI) URL: https://swarmtraces.org/ - How to keep enjoying programming in a world of LLMs Source: lobsters Topic: General (+AI) URL: https://discourse.haskell.org/t/how-to-keep-enjoying-programming-in-a-world-of-llms/14705 - Meta's Muse appears to use an OpenAI model labeled muse-special Source: hacker-news Topic: General (+AI) URL: https://mouse.dev/blog/muse-special/ - The cheap new AI model taking aim at OpenAI and Anthropic Source: hacker-news Topic: General (+AI) URL: https://www.ft.com/content/456884ea-2558-4648-8036-a77b73733430 - U.S. appeals court upholds designation of Anthropic as supply chain risk Source: hacker-news Topic: General (+AI) URL: https://www.cnbc.com/2026/09/25/pentagon-anthropic-ai-risk-appeals-court.html - Show HN: Hamilton – a no-internet Android health dashboard, named after my dog Source: hacker-news Topic: General (+AI) URL: https://play.google.com/store/apps/details?id=com.gads.hamilton&hl=en_US - Special Projects (2016) Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/special-projects/ - Tell HN: OpenAI $500 ProMax plan listed in API Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49841605 - LLM Policies: Progress At All Costs Source: lobsters Topic: General (+AI) URL: https://diegoe.be/2026/09/25/llm-policies-progress-at-all-costs/ - I stopped letting LLMs do arithmetic Source: hacker-news Topic: General (+AI) URL: https://medium.com/@jwbobbink/best-search-console-mcp-in-2026-gsc-wizard-7a63f91191ca - Goodbye Google Source: lobsters Topic: General (+AI) URL: https://robert.ocallahan.org/2026/09/goodbye-google.html - Paul Graham on LLMs 'Thinking' Source: hacker-news Topic: General (+AI) URL: https://twitter.com/paulg/status/2103135915195371973 - Lobsters: Rename vibecoding to llms (Greasemonkey script) Source: lobsters Topic: General (+AI) URL: https://greasyfork.org/en/scripts?by=1646191 ## Media - How to use Claude, Codex, and BYOK in GitHub Copilot for VS Code | GitHub Copilot Day Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=_Mqr5B3DLgM