TILens Daily Edition 2026-10-28 Filters: topic=ai, github=hidden Stats: 1099 articles, 27 sources, 1050 research papers Top topics: AI, AI Research, Information Retrieval ## News - Evernote turns AI-driven discovery into paid subscriptions Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/ads/customers/evernote - OpenAI and ServiceNow expand partnership across enterprise workflows Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/openai-servicenow-partnership-expansion - The future of the firm Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/the-future-of-the-firm - Legora is building the agentic operating system for legal work Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/legora - Legora is building the agentic operating system for legal work Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/legora-agentic-operating-system-for-legal-work - Using Your Own Embeddings in Spring AI 2.1 Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/10/28/spring-ai-upsert-own-embeddings - Spring AI 2.1 Message Parts: Reasoning That Survives the Round Trip Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/10/28/spring-ai-message-parts-reasoning-replay - Create an AI Voice Assistant with ElevenLabs and Node.js Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/voice_developer/create-an-ai-voice-assistant-with-elevenlabs-and-nodejs-15fc - Microsoft recorded $10 billion in revenue from OpenAI Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/28/microsoft-recorded-10-billion-in-revenue-from-openai/ - Creating AI value with enterprise context Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/28/1147709/creating-ai-value-with-enterprise-context/ - Anthropic engineer declares the coding interview dead Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/28/anthropic-engineer-declares-the-coding-interview-dead/5306115 - Anthropic just launched tools to show companies what their AI spending is buying Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/28/anthropic-just-launched-tools-to-show-companies-what-their-ai-spending-is-buying/ - 😸 WATCH: Robots That Learn Jobs by Watching You Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/watch-robots-that-learn-jobs-by-watching-you/ - Prompt Caching in Spring AI with Anthropic Claude Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/prompt-caching-in-spring-ai-with-anthropic-claude.html - Google announces Gemini 4 Carbon, its latest frontier AI model that you can't use Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/10/google-announces-gemini-4-carbon-its-latest-frontier-ai-model-that-you-cant-use/ - Google just handed its rivals the keys to Android Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/android-agents-build-debug/ - As AI agents reshape the web, Google opens Gemini and Search to more apps Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/28/as-ai-agents-reshape-the-web-google-opens-gemini-and-search-to-more-apps/ - My AI agent built a tank bot — then learned from losing 3 shots to 165 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/pokka-agent/my-ai-agent-built-a-tank-bot-then-learned-from-losing-3-shots-to-165-3k3a - Train a balance bot with reinforcement learning Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/28/train-a-balance-bot-with-reinforcement-learning/ - Three new discoveries in mathematics, computer science, and physics Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/28/three-new-discoveries-in-mathematics-computer-science-and-physics/ - Attacker Relentlessly Scans for Credentials by Impersonating AI Bots Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyber-risk/attacker-impersonates-ai-bots-scans-credentials - An AI assistant and emergency library that runs on your own computer Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/28/an-ai-assistant-and-emergency-library-that-runs-on-your-own-computer/ - [$] The campaign to push Northstar into Linux distributions Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1102738/ - Game Boy Color emulator running on a GitHub Universe badge Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/28/game-boy-color-emulator-running-on-a-github-universe-badge/ - Airbnb Cuts Recommendation Staleness from 2 Days to Seconds with Chronon Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/news/2026/10/airbnb-chronon-recommendation/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - From human clicks to agentic velocity: What OpenAI’s 1.2 billion scale means for your auth Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-agentic-identity-scale/ - Pairing industrial AI autonomy and human control Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/28/1147637/pairing-industrial-ai-autonomy-and-human-control/ - How to Auto-Resize Cross-Origin iframes Without Breaking Security Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/gallerydock/how-to-auto-resize-cross-origin-iframes-without-breaking-security-3ffe - Google’s AI worlds can now talk back Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/google-ai-worlds-can-now-talk-back - 😺 Google launches Genie 4 with sound Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/google-launches-genie-4-with-sound-f71a/ - In-Process Inference vs Calling a Service: ONNX Runtime and DJL Against a Remote Model Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/2026/10/in-process-inference-vs-calling-a-service-onnx-runtime-and-djl-against-a-remote-model.html - Inside Mithril, the One-Employee Biotech Anthropic Acquired Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/inside-mithril-one-employee-biotech-anthropic-acquired/ - Oracle AI Workspace Promises Business Workflows Through ChatGPT Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/oracle-ai-workspace-chatgpt-business-workflows/ - Everything That Happened in AI Today (Wednesday, October 28, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-october-28-2026/ - VCs will make billions on Anthropic’s IPO, but Amazon is set to make much (much) more Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/27/vcs-will-make-billions-on-anthropics-ipo-but-amazon-is-set-to-make-much-much-more/ ## Research - How to Make AI Work for End-to-End Business Processes Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-make-ai-work-for-end-to-end-business-processes/ - Where a Cell Sits Matters More Than How Many There Are Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/where-a-cell-sits-matters-more-than-how-many-there-are/ - Building and Visualising Kolmogorov–Arnold Networks Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/building-and-visualising-kolmogorovarnold-networks/ - Your RAG Pipeline Is Missing a 1994 Algorithm Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/your-rag-pipeline-is-missing-a-1994-algorithm/ - Dynamic Multi-Step Decoding for Time-Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34409 - SCAFFOLD under Hessian Similarity: Sharp Convergence Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35663 - On the stability of learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35856 - CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35313 - SATFormer: Learning When to Use Early Value Residuals in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03953 - A Multimodal Machine Learning Framework Integrating Genomic, Epidemiological, Environmental, and Clinical Imaging Data for Accelerated Measles Detection and Transmission Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32996 - High-resolution tactile observation makes hidden racket-control mechanisms learnable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35563 - Trust Region Continual Learning as an Implicit Meta-Learner Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02417 - Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35280 - The Noise-Transmission Burden of Diffusion Network: Why Image Prediction Can Outperform Noise Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34834 - Uncertainty Evaluation to Support Safety of the Intended Functionality Analysis for Determining the Applicability of Performance Targets Across Triggering Conditions in ML-Based LiDAR Object Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35092 - A Battery for AI Propensity Measurement: Rubrics, Synthetic Item Banks, and Annotations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34614 - From Intelligence to Autonomy: Foundations and Construction of Autonomous Agents for Future Intelligent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33445 - ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35568 - Automated screening of Parkinson's Disease using Smooth Pursuit Eye Movements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33359 - Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33437 - Individual Fairness via Local Predictive Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33285 - Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17668 - An Agentic AI Workflow for Liver Lesion Segmentation and Structured Radiology Reporting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34599 - Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34177 - Learning What to Share: Expert Specialization for Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33822 - Provably Efficient Q-learning for Robust Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35656 - SVD-Attention: Efficiently Analyzing Attention Blocks in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34971 - Discovering and Reasoning of Causality in the Hidden World with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.03941 - FG-ConvNO: A Geometry-Aware Neural Operator for Propeller CFD Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33456 - Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35123 - mdRNAcat: A Molecular Dynamics RNA Catalog of REST2 Conformational Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35204 - Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.14586 - COPE: Composable Performance Emulation for Mixture-of-Experts Offloading Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33404 - Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35345 - Outcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34385 - Constrained Gradient Equilibrium: Approachability under Locally Constrained Adversaries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33985 - Ambiguous Fits: The Rashomon Effect and Challenges in Scaling Law Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34514 - When is early stopping beneficial under label noise? A phase diagram for kernel gradient flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33846 - Gaussian Approximation for Composition and Subsampling of Differentially Private Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33333 - When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33011 - UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33013 - Interpretable Brain Age Prediction Using White Matter Fiber Orientation Distributions with Rotation-Equivariant Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34825 - When Are Nesterov Trajectories Eventually Locally Minimizing? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33341 - GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02518 - Evaluating Spiking MoveNet Deployability for Near-Future Onboard Spiking Satellite Pose Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33061 - Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33671 - One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33794 - Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35652 - Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34021 - How Geometry Shapes Generative Model Evaluation on Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33731 - Grounding on Request: Learning Modality Control in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33841 - Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33527 - Minimax Rates for Conditional Generative Learning under Wasserstein Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35490 - RoboJev: An Open Vision-Language Judge for Robot Success Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33718 - Can Language Models Learn While They Think? Testing Gradient Adaptation Across Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33025 - How Much Graph Is Too Much? Graph Construction and Exposure in Spatio-Temporal Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34611 - ProMo3D: Probing Motion Cues in Frozen 3D Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33802 - Discovering Topics from Linear Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34739 - A Unified Analysis of Importance-Corrected Momentum Actor-Critic over a Markovian Trajectory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33477 - A Gaussian Process State Space Formulation for Materials Constitutive Modeling: Application to Quasi-brittle Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33175 - BE-CTDE: Blockchain-Enabled Multi-Agent Reinforcement Learning with Anomaly Detection and Token Economics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34121 - Centralized Critics for N-Agent Ad Hoc Teamwork Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34799 - Leveraging Dale's Principle as an Inductive Bias in Recurrent Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34052 - When Does Cheap Physics Help? Gated Multi-Fidelity Physics-Informed Networks with Provable Sample Savings and Conformal Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01176 - Patch-Derived or Register Tokens? Comparing Variable-Length Image Tokenizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33540 - Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34043 - False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33026 - Generative Anchored Fields: Endpoint Learning for Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22693 - Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16615 - Nowcasting aerosol particle size distributions from PM2.5 with physics-regularized flow matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33557 - Vib2ECG: A Co-Located Chest-Lead SCG-ECG Dataset and Benchmark for ECG Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15539 - FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16648 - Constrained Extreme Gradient Boosting for Parametric Proper Orthogonal Decomposition Subspace Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04130 - Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35817 - Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34828 - AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33017 - One-Shot Federated Model Editing for Device Dynamics at the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35212 - Recovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34850 - Learning the Past from the Future: Retrospective Reconstruction in Temporal Interaction Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33171 - Improving the Performance of Compressed Transformers with Post-Hoc Embedding Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14635 - Multi-view Semantic-aware Resource Allocation for Edge AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34532 - Automated identification of ivory carvings using machine learning: A proof-of-concept approach to detecting the illegal wildlife trade Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33243 - AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34890 - Mapping the Solution-Set Structure of Grokking on Latin Squares Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35036 - Greedy Orthogonal Polynomial Manifolds with Lipschitz Control for Dimensionality Reduction and Reduced Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33784 - Subspace Crystallization in Grokking: Rank Compression Tracks the Phase Transition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35112 - The Geometry of Limits in ReLU Function Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33779 - Ampe-DB: A Dataset for Human Activity and Interaction Analysis Using the Ghanaian Game Ampe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33130 - On the Architectural Complexity of Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04325 - COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15200 - Performance Gaps Between Open-Loop, Certainty-Equivalent, and Optimal Control Under Action-Dependent Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33412 - Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34638 - Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04971 - TRACE: Memory-Efficient Time Series Class-Incremental Learning via Temporal-Spectral Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35727 - XL MIMO Extreme Learning Machines: Wave-Domain Inference with Stacked Metasurfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35469 - Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35079 - TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33776 - Adapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35636 - Valid Early Detection of Memorization in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34617 - OneEEG: A Unified Signal-Visual Multimodal Language Model with Task-Aware Mixture of Projectors for Multi-Task EEG Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35355 - Sharp Bounds on Continuous Treatment Effects under Unobserved Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33278 - Uncertainty Quantification for Financial Foundation Models: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33109 - Reinforcement Learning for Controller Parameters in the Auto-Bidding System at Pinterest Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33248 - Multi-Horizon Future Discovery for Physics-Informed Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35468 - Vision Token Pruning via Query-Vision Interaction Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33215 - Approximate Universal Prediction under Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33842 - CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34208 - Linear-Time Context Compression with State-Space Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33006 - Improving Reasoning with Rollout Agreement for Group-Based Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34951 - Linear Probes Transfer from Base to Distilled Language Models despite Rotation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35586 - Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27742 - PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.00910 - SymADiT: Symmetry-Aware Crystal Generation with Latent Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10115 - Neural Eigenfluid Bases: Spectral Objectives, Gauge, and Topology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33925 - LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33465 - Fantastic Pretraining Optimizers and Where to Find Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02046 - Sliding Networks: A Family of Residual Structures Preserving Feature Learning and Feature Diversity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33840 - EpiFlow: Bridging Safety and Performance in Offline Reinforcement Learning via Epigraph-Guided Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08054 - The Clustering Occupation Kernel (CLOCK) Method for Time Series Arising from Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33354 - Wave Is All You Need: A Quantum Language Model Based on Fully Connected Quantum Boltzmann Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34492 - PENEX: AdaBoost-Inspired Neural Network Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02107 - Accelerating SO(2)-Equivariant Materials Models through Low-Precision Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35164 - Transformer to GPT-5: Advancements, Limitations, and Future Directions in Large Language Model Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34281 - RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33625 - Multiple Importance Sampling for Guided Speculative Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33368 - Is Oracle Pruning the True Oracle? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.00143 - Sparse Reconstruction by Direct Measurement-to-Field Generation in Function Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34709 - Edge-Centric Adaptive Neural Activation via Parametric Tanh Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34154 - MOFjson: An Explicit Topological Representation of Metal-Organic Frameworks for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34549 - Beyond Deduplication: Sharp Retrieval Limits for Attention with Correlated Distractors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34682 - Faithful Federated Tabular Data Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33403 - AgriDefend: A $205 Offline Edge Device that Detects Crop Stress Before Visible Symptoms via Multimodal AI Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34861 - FOCUS: Active Critic Learning for Long-Horizon Language Model Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35801 - Error Diffusion Replaces Latent Weights: Training Binary-Weight Language Models on a Few Bits of Dithered State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34566 - Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33882 - CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16700 - Error-Subspace Calibration for Multi-Task Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33483 - Bridging the Divide: End-to-End Sequence-Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25126 - Models Verify Sufficiency, Not Validity: Usable Falsehoods Evade the Checks that Gaps Trigger Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34488 - Learning Force-Reactive Humanoid Loco-Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35862 - Intrinsic Gradient Barriers in Pushforward Deep Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34484 - VulDec: Vulnerability Detection in Binaries via Neural Decompilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33716 - Adversary Brains: Hypothesis-Based Logical Signatures for Threat Actor Detection with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35624 - Collective Collaboration of Recursive Autonomous Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33515 - InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2306.08757 - A Measure-Geometric Theory of Robustness in Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33123 - Support-guided OOD Removal with Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33194 - Identities, Not Pairs: Distribution-Free False-Accept Control for Embedding-Based Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35277 - Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33849 - Real-Time Human Trajectory Prediction from RGB-D for Mobile Robots Using Bi-Mamba Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33916 - Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34182 - AdaTutor: Adaptive Tutoring through Pedagogical Strategy Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34659 - Rank-1 Weight-Corrected Trainable Weight Averaging for Out-of-Distribution Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33909 - Entity-Aware Evaluation of OCR Systems for Historical Document Transcription Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33004 - Inference Latency-Aware Tsetlin Machine Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35304 - Reversion, Retention, and Semantic Intervention: Measuring Functional Content in CLIP Fine-Tuning Deltas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34144 - One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34623 - Flow Mesh: A Velocity-Regularized Flow Matching Framework for Stable Distributional Modeling of Physical Fields on Unstructured Meshes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33204 - Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35833 - Audit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35716 - Software Engineering LLMs: Why We Need Them and How Software Engineering Helps Build Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33851 - Blendshape Generation for Models with Disconnected Parts: Adding ARKit/MediaPipe Blendshapes to Anime-Style Character Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35076 - Spherical Brownian Diffusion for Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35101 - Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34923 - Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35609 - AmbientFM: A Foundation Model for Ambient Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11200 - Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35244 - TCSP3.0: Template-Based Crystal Structure Prediction with Coefficient-Preserving Element Substitution and Structural Diversity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34029 - Performance of Neural Operator Baselines on 'The Well' Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33967 - How Much Fresh Data Should CTR Recalibration Use? A Temporal Evaluation of Post-hoc Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33168 - FedSEAM: Federated Continual Learning of LLMs via Subspace Expert Agreement Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33496 - OrthoRF: Exploring Orthogonality in Object-Centric Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35203 - A Distribution-Matching Perspective on LLM Training Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33740 - Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33180 - Projection-Based Federated Learning on Compact Submanifolds with Geometry-Independent Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33712 - Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34009 - Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33129 - Relational Composition as Parallel Transport: What Per-Entity Frames Force in Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34945 - Diagonally-Weighted Generalized Method of Moments Estimation for Gaussian Mixture Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20459 - Adapting Neural Posterior Estimators for Simulation-Based Inference in Agent-Based Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07413 - Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34140 - Partial Modal Tensor Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34008 - Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15194 - The Information Geometry of Representation Formation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34015 - RBGA: Residual-Budget Guide Arbitration for Offline-to-Online Safe Reinforcement Learning in Dexterous Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33494 - Smoothness Errors in Dynamics Models and How to Avoid Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05352 - Good Rankings, Poor Choices? Rethinking Language-Only Vision-Language Model Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34685 - Recursive Semantic Divergence for LLM Agent Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33012 - Precedence-Aware Resource Allocation: Extending the AUTOC Framework to Multi-Level Treatments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34812 - Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34159 - $\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10981 - Risk-Aware Output Control Should be the Focus of Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35052 - Geodesic-SVDD Latent Mixup for One-Shot Distributed Tabular Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33619 - A Hierarchical Method for Environmental Sounds Recognition in Complex Acoustic Scenes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34931 - Can System-1-Style Decision Models Replace Dedicated Rerankers in RAG? A Systems Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34816 - The Long Delay to Arithmetic Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13082 - Prior-Data Fitted Networks for In-Context Off-Policy Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34035 - Holo-NN: Holographic Nearest Neighbor Search via Compressive Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33224 - GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17515 - AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15038 - Learning Pathology-Sensitive Representations for Unsupervised Retinal OCT Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33143 - Stable and Calibrated Latent Force ODE Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33939 - Macro Mondrian Conformal Risk Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35035 - One Call Ahead: Packed Self-Speculative Decoding with Diffusion Drafting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33379 - Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21073 - Birth, Death and Diff: Insertion-Based Sequence Generation with Corrections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34310 - SRA: Selective Residual Adaptation for LLM Reasoning Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34199 - Proofs of strong forms of the Bovdi--Geche universality conjecture and a complex analogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35645 - ARMD-Predict: multi-site machine learning to predict antibiotic resistance before culture results Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32998 - FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06984 - When Respondents Are Scarce: LLM-Derived Semantic Priors for Bayesian Confirmatory Factor Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34843 - Explicit Frictional Contact Modeling in Neural Garment Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33492 - Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07600 - Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35804 - Not All Mislabels Are Equal: Efficient Task-Aware Auditing with Confidence Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33262 - CounterFlow: Target-Conditioned Flow Matching for Visual Counterfactuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35679 - GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33277 - Minimax Regret for Sobolev Kernel-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34045 - EEGBiFormer: Real-Time EEG Attention Classification via Hybrid CNN-Transformer with EEG-Informed Auditory Protocol Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33832 - Unified Robust and Convergent Over-The-Air Federated Learning under Channel Noise and Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.19549 - Kernelised covariance matrices, dimension reduction and imbalanced spectral clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33177 - NoiseFormer -- Noise Diffused Symmetric Attention Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11619 - Reinforcement learning for constrained stochastic linear--quadratic control in continuous time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34995 - Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33479 - Approximate Unlearning in Prototype-based-classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34495 - Fully quantum training of parametric circuits with Quantum Hamiltonian Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33144 - Stable Dimensionality Reduction via Isometric Centroid-Encoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33872 - HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34589 - Beyond Modeling Order: Dual-Path Spatiotemporal Representation Learning for Cross-Subject EEG Emotion Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35540 - ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34386 - A quantum k-nearest neighbors implementation using magnitude-aware comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33739 - OvisOCR3 Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33066 - Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33623 - Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06908 - Extrapolating learned dynamics across bifurcations based on generalized synchronization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34471 - Sequential versus fully conditional specification for tree-based synthesis of health data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35163 - Online Covariance Estimation for Averaged Stochastic Gradient Descent on Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33419 - Beyond feature attribution: Recovering latent interaction structures in machine learning models via localized CBFI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34962 - Random-Bridges as Stochastic Transports for Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14190 - Efficient Proof Generation for Lean Statements with Multiple Candidate Answers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34490 - Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.19195 - Min-Marginal Power Indices for Multi-Objective Feature Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33885 - Embedding-Based Educational Taxonomies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33694 - KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13226 - Model reduction in time: Learning flow maps for reducing stochastic dynamical systems in time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35504 - T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34103 - Affine-invariant Cubic Newton with Weak Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33516 - Efficient Linear Attention for Multivariate Time Series Modeling via Entropy Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03190 - Inference-Time Prior Adaptation for Imbalanced Data Streams under Concept Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33126 - TRON: Transferring Naturally Evolved Network Architectures into Neuroevolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35647 - Can JEV Support Clinical Trial Criteria Assessment? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35721 - The Cost of an Unknown Horizon for the Last Iterate of Clipped SGD under Heavy-Tailed Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33381 - GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35480 - DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34272 - A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34934 - Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35866 - DualPace: Decoupled Scheduling and Cooperative GPU--CPU Decoding for LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33501 - Best Policy Tracking in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34501 - LUCID: Local Understanding of Covariate Importance with Conditional Density Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35740 - Conversational Generalized Linear Bandits with Hybrid Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35262 - Online Learning in Stabilized Linear Dynamical Games with Adversarial Disturbances Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.18814 - From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24555 - Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22681 - Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33310 - Coder as Editor: Code-driven Interpretable Molecular Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.14455 - How Do Small Coding Agents Use Code Graphs and Embeddings? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33958 - Interpretable and Steerable Molecular Graph Generation using Concept Bottlenecks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34227 - Reinforcement Learning Done Right for Explicit Confidence Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35059 - Cross-Attentive Bayesian Low-Rank Adaptation for Multimodal Uncertainty Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16657 - Speculative Decoding for Mixture-of-Experts Models: Expert Bytes, Kernel Bandwidth and the Best Draft Length Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34440 - Learning Population Dynamics with Variational Doob-Wasserstein Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33922 - Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33956 - Shared Context, Separate Engines: Streaming Vision--Language Inference on Edge SoCs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35309 - Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35736 - IsoAct: Geometry-Aware Post-hoc Debiasing via Isometric Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34690 - OpenESM: Energy-Steered Models Are Scalable Foundation Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33005 - All-in-One: A Composable Attack on LLM Transformations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33298 - The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35411 - Feature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33030 - Model Selection for Off-Policy Evaluation via Pairwise Bellman Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35748 - H-GLow: Accelerating Graph Generation via Hazard-Guided Discrete Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33599 - RadonBench: A Benchmark of Classical and Learning-Guided Search Techniques for Problems in Combinatorial Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33259 - Counterfactual Test-Time Augmentation for Shortcut Removal in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33904 - Learning Representative Port Subsets for Efficient Fluid Antenna Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33730 - Adaptive Memory Index Evolution for Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34977 - UTA: Universal Training Adaptive Learning Rate Decay Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35113 - Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34375 - Beyond Affine Reconstruction: Multi-Resolution Transformer DeepONets for the Radiative Transfer Equation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33668 - When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33311 - Bug Severity Classification with Fine-Tuned Open LLMs: A Paired Comparison with TF-IDF and CodeBERT Baselines on Eclipse Reports Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34127 - Organon : From Evolutionary Search to Recursive Self-Improving Agents for Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33046 - Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33029 - Security of Deep Reinforcement Learning for Autonomous Driving: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2212.06123 - Improving VLMs on Scientific Chart Analysis via Autonomous Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35077 - Stable Continuous-Time Consistency Distillation: An Empirical Study with a Multistep Extension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34704 - Reactive Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33826 - Balanced Sampling in Stochastic Multi-objective Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35551 - Spatially Aware Dictionary-Free Koopman Eigenfunction Identification for Modeling and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22648 - Explainable Prediction of High-Speed Solar Wind Streams driven by Coronal Holes via Topological Data Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35549 - SHIFT-JEV: Certified Abstention and Gain-Gated Continual Adaptation for LLM-Based Decision Models under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34329 - Targeted Deep Regression - Initial Applications in Whole-Body Water-Fat MRI in UK Biobank Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35339 - Model-agnostic predictability quantification of multivariable time series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33209 - Tree Depth and Sample-Quality-Associated Features: Two Hidden Factors in Boruta Selection for RNA-Seq Data Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33307 - Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35514 - BriLLM-MetaPred: A Representation-Prediction Unity Language Model with Adaptive Self-Measurement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34018 - Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35560 - A knowledge-driven nonconvex square-root regularization framework for joint group sparsity and structured smoothness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35428 - Temporal-Difference Calibration of Black-Box Simulators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35311 - Joint End-to-End Training of Weighted BP Decoder Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33559 - Correlation-Aware Exploration for Long-Trace Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34949 - Adaptive Transfer of Representational Signatures for LLM Reliability Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33442 - AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34384 - STeP-TS: Shared Temporal Filters with Pruning for Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35128 - MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35697 - SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35215 - ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35606 - EF-LLM: A Continual Learning-Based Framework for AI-Assisted Automation, Enhanced Sparse Prediction, and Hallucination Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.00852 - Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34942 - Machine Learning Applications in the Solar Interior and Atmosphere Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34687 - Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.07675 - Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34258 - Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08032 - TransECG-SSL: Hybrid Self-Supervised Representation Learning for ECG Arrhythmia Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35378 - IntNet: A Communication-Driven Multi-Agent Reinforcement Learning Framework for Cooperative Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34466 - Conditional Diffusion Generation of DVL and Inertial Signals for Underwater Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34574 - MOSHO: A Native Discrete Shark-Inspired Metaheuristic for Hardware-Aware Neural Architecture Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33358 - Realizing Low-Precision Storage and Sparse Execution in a Folded FPGA Speech Enhancer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35144 - Amplify, Locate, Estimate (ALE) on Rare-Failure Rates of Fine-Tuned LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35472 - When Does Data Value Reduce to Class Balance? A Coverage View of Per-Point Data Valuation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34801 - Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18379 - Towards a Learnable Retriever for Textual Graph Question Answering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33511 - TempShap: When and How Much a Feature Matters in Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33330 - CAMEL-CLIP: Channel-aware Multimodal Electroencephalography-text Alignment for Generalizable Brain Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13272 - Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34650 - MetaARIMA: Configuration-Level Transfer Learning for ARIMA Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34171 - HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34126 - Latent dynamics for reconstructing fine-scale PDE trajectories from coarse observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33722 - FlexMARL: Graph-Driven Rollout-Training Co-Design for LLM-Based Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09578 - Quantifying the failure of symmetry learning in linear diffusion models due to initialization and finite-sample effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35720 - Global $\mathcal{O}\left(k^{-2}\right)$ Convergence of Multilevel Gradient-Regularized Newton Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35195 - Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34756 - Cumulative Marginal Matching for One-Step Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34575 - Exact Unlearning After Data Curation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33426 - ScaleRLT: Exact Log-Probabilities and Fast Deferred Rollouts for Reinforcement Learning on Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34427 - Detecting bus delays and service anomalies in Niter\'oi with autoencoder latent feature representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35710 - Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21978 - Generalized Wasserstein Flow Matching: Nested Couplings for Point Cloud Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08424 - Does VGGT Know What It Does Not Know? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35806 - Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12049 - Certifying Distributionally Robust Decisions from Projection Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34493 - Non-Ergodic Markovian Mirror Descent with Unbounded Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34433 - Directional Attention Guidance for Diffusion Models via Sparse Hopfield Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02531 - EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33930 - Why Does Structured Output Fail? An Empirical Study of Prompt-Enforced Pydantic Schemas Across Nine LLMs Source: arxiv-cs-lg Topic: AI Research (+AI, FastAPI, Python) URL: https://arxiv.org/abs/2610.33949 - Efficient probabilistic weather forecasting at quarter-degree resolution with two-sided transport attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35545 - Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34137 - On shallow feedforward neural networks with inputs from a topological space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.02321 - $\Delta\tau$-Bench: Pushing Agents Toward a Moving Capability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34238 - Alignment via Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34242 - A JiT-Based Denoising Defense Method Against Adversarial Examples for Radio Signal Automatic Modulation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35084 - Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35329 - QECGBERT: A Scalable ECG Foundation Model Based on Self-Supervised Language Learning via VQ-VAE Waveform Tokenization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33964 - EviGround-CT: Sentence-to-Volume Grounding for Verifying LLM-Generated Chest CT Reports Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33038 - InterQ-RL: Interaction-Aware Correction of Execution Mismatch in Quantized Agentic RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35303 - Polynomial Residual Networks are Generically Identifiable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33738 - Models Designed to Forget: Machine Unlearning via Key Deletion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15033 - Lumbermark: Resistant Clustering by Chopping Up Mutual Reachability Minimum Spanning Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07143 - Lower expected Fisher rank implies better PAC generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33208 - Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33096 - Intrinsic Information Rates of Summaries in Simulation-Based Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34703 - AT-AT: Automatic Tool Optimization from Agent Traces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34679 - Finite-Sample Sensitivity of Kernel Metrics for Generative Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34477 - Does Notation Matter? MusicXML Tokenisation for Symbolic Music Generation and Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34247 - A theory of noisy linear recurrent neural network learning dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35785 - Attention under Bounded Key-Query Similarity: Space Complexity and Transformer Anisotropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35020 - Label Ensemble Perspective for Reduced-Complexity Graph Node Classification under Label Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.11020 - The Symmetry of Differential Neural Tangent Kernel under the Orthogonal Group Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34023 - Optimizing Physical Neural Networks through Device Variable Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33522 - TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34519 - Beyond Wasserstein Proximity: Finding Better Transfer Sources Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35314 - Reinforcement Learning for Adaptive Crowd Flow Control Using Dynamic Barriers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34163 - Pro-Active Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34681 - Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35582 - Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35733 - Augmentation-Guided Adversarial Training via Local Stability-Based Sample Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33331 - Exploring perceptual straightness in learned visual representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34678 - Modeling Liquid-Cooled Data Centers in EnergyPlus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33148 - Work Agents: Systems, Capabilities, and Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35845 - Numina Fuse: Interactive Autoformalization in Lean 4 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33860 - Information-Theoretic Scaling Laws for Generative Diffusion Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33337 - Memory or a Clock? Auditing a Memory Advantage in XLand-MiniGrid with Seeds, Maps and Evaluation Noise Apart Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33816 - End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34462 - Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33788 - Video World Models Need Predictable Latents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34663 - Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35426 - Artificial Intelligence in Mechanical Engineering: Foundations, Opportunities, Challenges, and Responsibilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33105 - Cross-User Adaptation for sEMG Gesture Recognition via Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34011 - TUON: A Tensor-Aware Optimizer Utilizing Tensor-SVD and Polarization for Large Language Model Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35130 - Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35398 - From GPU to TPU with Coding Agents: What Works, What Fails, and What It Costs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34422 - End-to-End MXFP8 Reinforcement Learning on Blackwell: What Matching Buys, When It Pays Off, and How It Fails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34915 - Neyman Orthogonal Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33217 - A SegFormer-based model for spatial Daylight Factor prediction with comprehensive obstruction encoding and regulatory validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33737 - Image Clustering with Vision-Language Model Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33265 - Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.20062 - A Nonconvex Framework for Joint Sparse Sample Weighting and Parameter Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33957 - AutoPRL: Automated Path Representation Learning via a Learnable View Generator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35032 - Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33845 - INTRA: Interleaved Non-contiguous Token spaRse Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34056 - DIGEST: Discovery-Guided LLM Tuning for Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33880 - Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35070 - AudioFM: Towards General Purpose Audio Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34183 - Quantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35715 - Joint Independence Testing for Latent Position Random Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34544 - BellowsKV: One Latent for Many Layers, Expanded on Demand Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35023 - GNN-VIEW: Visual Inspection and Explanation of Graph-based Earth-System Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35693 - Activity Recognition from Smart Insole Sensor Data Using a Circular Dilated CNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04477 - Streaming Recurrent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34833 - Synthetic Data Augmentation for Functional Data: Wasserstein Risk Bounds and Diffusion-Based Conditional Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34120 - CFL-aware edge design for graph neural solvers of hyperbolic transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33769 - An Empirical Study of Reinforcement Learning Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33420 - From Human Intent to In-Orbit Action: A Self-Learning Large Language Model Agent for 6G Satellite Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34387 - Controlled Block Proximal Linearized Method for Nonconvex and Nonsmooth Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34390 - Rectified Language Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33811 - Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34173 - Prior Predictive Matching for Bayesian LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35457 - EdgeDeID: A 0.6B Clinical De-identifier Trained Without Real Patient Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33839 - Query Complexity of Learning Axis-Aligned Partitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35495 - Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10418 - ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35486 - Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33024 - TimeWorld: Towards Action-Conditioned Multimodal World Models for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34797 - Physics Informed Neural Networks for Solving the Drift-Diffusion Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33133 - SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34365 - Clustering of High-Dimensional Human Gene Score Data for Target Cell Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33531 - Counterfactual Model Testing Under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33594 - A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35658 - Sparse Sum-of-Squares Layers for Certified Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34590 - Benchmarking System One Models for Time-Series Decision Making: A Case Study of Jev Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33410 - Constraint Learning by Optimizing over Trained Neural Networks: A Pragmatic Tutorial Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35505 - Benchmarking uncertainty quantification for engineering regression under graded distribution shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35356 - From Explaining to Enabling: Actionable Transparency in Algorithmic Insurance Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34459 - AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33245 - Overlap-Aware Sub-hypergraph Pattern Frequencies for Hypergraph-Level Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33514 - Climate downscaling with likelihood functional flow matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33482 - Evaluating Bayesian deep learning for robust biomedical time-series classification under distribution shift: A sleep scoring case study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35484 - Understanding Practical Optimization in Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35209 - An actively trained neural operator for near-explicit atmospheric chemistry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33771 - Beyond Physical Illness: Can Clinical Narratives Reveal Emerging Mental Health Risks in Chronically Ill Patients? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35761 - When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35497 - LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35190 - EmoNet: A Lightweight Attention-Based CNN for Speech Emotion Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33977 - Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34976 - Cross-Loop Query Handoff: How Later Loops Redirect Two-Hop Retrieval in the Ouro Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34639 - One Megakernel is Not Enough: Predicting Where to Cut for Streaming Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35336 - Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35706 - Hessian-Similar Optimization with Capped Participation: Lower Bounds and Virtual Masters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33835 - Distilling neural networks into equations to predict planetary instability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35617 - Position: Adopt Constraints Over Fixed Penalties in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.20628 - Variational Atlas Autoencoders and Self-Supervised Chart Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33577 - On the Error Analysis of Triangular Transport Maps for Conditional Generation via MMD-based Objectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33610 - Automatic Configuration of LLM Post-Training Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18773 - Checkpoint Reload Explains Most of the Measured State Gap in Two State Discovery Reproductions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34891 - Efficient Exact Unlearning for Federated Zeroth-Order Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35211 - Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33732 - StateWise: Teaching Language Models to Track and Obey Evolving Constraints in Multi-Turn Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33766 - SearchHorizonBench: A Benchmark for Search Value in AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34714 - Graph Neural Networks for Supply Chain Management: A Framework and Real World Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.08550 - FeatureLoop: Benchmarking Coding Agents under Evolving Requirements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35488 - Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35766 - NOMAD-EEG: Native Omni-Montage Adaptive Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35246 - A Sign Law for Entropy Drift under Sampler Mismatch in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34044 - Multitask Interactions in Recurrent Dynamics across 100 Cognitive Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33926 - Enhancing Type 2 Diabetes Diagnosis with Evolutionary Algorithms and Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34123 - Hierarchical Cooperative GFlowNets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33968 - Priority-Preserving Advantage Aggregation for Multi-Reward Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34862 - Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10230 - MINT: Mitigating Structural Inconsistency via Attentive Message Passing for Financial Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34950 - S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35518 - Biology-Guided Context-Aware Residual Propagation for Spatial Gene Expression Prediction from Histology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35167 - Resolving the Mobility-Equity-Emissions Trilemma: A Causal Machine Learning Framework for Dynamic Tolling Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33994 - DAC-Loop: Distillation-Aware Compression for Remote Sensing CNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35175 - LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34901 - Last-Iterate Stationarity of Muon with Finitely Many Newton-Schulz Iterations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34158 - Flowette: Flow Matching with Graphette Priors for Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23566 - Large Language Models: A Plain-Language Overview for Engineers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34585 - HIFI: A Highly Efficient Framework for Statistical Inference with Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34550 - Accuracy and efficiency of compact foundation models for surface-water mapping during floods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34904 - FlowGenesis: Representation-Driven Self-Organization of Neural Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35108 - LSTM-Style Looped Transformers with Shared KV Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33360 - Does "Do Differentiable Simulators Give Better Policy Gradients?" Give Better Policy Gradients? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18161 - Locked In: Multi-Objective RL for the AI Data Center Build-Out Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35147 - Selective Tie Learning: Mitigating Spurious Correlations in Preference Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35787 - Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33145 - Satellite-derived bathymetry of Arabian Gulf ports under leakage-free validation: a multi-site benchmark of empirical, machine-learning and deep-learning models against 285,000 multibeam soundings, with an outlook for UAE waters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33609 - MLIPDiff: Guiding Denoising Diffusion Models for Structure-Based Drug Design via Machine-Learned Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33315 - EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35464 - Computational De Novo Design of Miniprotein Candidate Neutralizers Targeting the IL-23 Cytokine Subunit p19 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32779 - ProtoEEG: Structured Prototype Alignment for EEG Visual Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33065 - Detecting Temporal Concepts in Video Transformers via a No-False-Positives Test Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33353 - A Computationally Efficient Non-Interpolation Virtual Trellis Approach for Mammogram Gradient-based Patterns Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34352 - Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35226 - Steering the Teacher: Improving On-Policy Self-Distillation for Thinking Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34005 - Execution Logs Sway VLM Judges of Robot Progress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34151 - Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36544 - LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37570 - LESSRec: Level-Specific History Modeling for Semantic ID-Based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37286 - From Generation to Scoring: Scaling LLM-Based Semantic Labeling at LinkedIn Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36383 - Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37280 - Hypergraph-Enhanced Evidence Selection for Long-Context Multimodal Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35542 - LRanker: Scaling LLM Ranking to Millions of Candidates with Test-Time Scaling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.27810 - Counterfactual Profile Perturbations for Recommendation Explanations: A Reproducibility Study Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36208 - When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37358 - GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37267 - Cross-Day Compatibility of Daily Item Embeddings: An Empirical Study of Alignment, Scale Management, and CTR Adaptation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36408 - REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37584 - KL-MOPD: Discrepancy-Aware Multi-Objective On-Policy Distillation for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36973 - The Vocabulary Is Already Here: Adapting Pretrained Interpretable Features for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36763 - Tessera: Structure-Completed Evidence Units for Web Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37080 - Validating FKG.in: Soundness Assessment in LLM-Augmented Indian Food Knowledge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.29249 - LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.18239 - QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36557 - MAREval: A Multi-Agent Framework for Evaluating Natural Language Recommendation Explanations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36389 - Can Complementary Signals Bridge Similarity Islands? Manifold-Augmented Graph Embedding for Multimodal Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37409 - When Do Pretrained Audio Representations Help Music Recommendation? A Study Across Ranking and Generative Interfaces Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.06928 - TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.25147 - Scoring-Rule Sensitivity in LLM Evaluation: Evidence from Indian Financial Regulatory Text Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.19298 - Recall or Relearn? A Mixture of In-Context Experts for Recurring Concept Drift Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36585 - CMASS: A ClimbMix Agentic Search Suite for Evaluating Search Agents Across Heterogeneous Tasks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.20317 - Compote: Collapse-Resistant Multiple Hypothesis Learning For Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37005 - Inherit4Rec: Parameter Inheritance for Efficient Scaling of Recommendation Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.23111 - PailitaoMMSearch2.0 Technical Report: Scaling Generative Retrieval to Unified End-to-End Multimodal Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36958 - TaskBridge: Technical Report for SIGIR 2026 eCommerce Challenge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37231 - Governed Sovereign RAG for Public Administration: Tripartite Epistemic Routing, Facet-Guided Clarification, and Deterministic Numeric Verification in Citizen Services Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36561 - AutoRSE: Evaluating LLM Agents as Recommendation Engineers for Self-Evolving Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37228 - RELAY: One Query, Two Roles for Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36000 - Unified Heterogeneous Feature Interaction via Effective-Rank Scaling for Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.35318 - Comparing GenAI to Machine Learning and Manual Review for eDiscovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.16925 - Latent Residual Reasoning for Ranking in Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36890 - Coverage Under Contradiction: A Benchmark for Negation-Aware Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37162 - DuTri: Dual-Branch Modeling with Triadic Factorization for Multimodal Multi-Scenario Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36836 - ACOR: incremental evidence accumulation towards real-time DNA storage reconstruction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36500 - Preserving rare-item recall under a storage budget: quantization, distillation, and the limits of teacher fidelity Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36267 - BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36239 - Lossless Compression of Proximity Graph Indexes for Efficient Approximate Nearest Neighbors Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37176 - SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36991 - Rethinking Positional Encoding and Interaction Granularity for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37140 - When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36134 - CCP-DP: Cross-cluster context-guided phase dynamic programming for DNA storage sequence reconstruction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36559 - Role-Augmented Intent-Driven Generative Search Engine Optimization Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2508.11158 - When Diffusion Recommenders Stop Sampling: Preserving Generative Diversity Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36954 - Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.11115 - Is the education gap in generative AI use smaller than the internet's was at a similar level of use? Evidence from 16 European countries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36181 - DeGenTWeb: A First Look at MGT-dominant Websites Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.00087 - Do We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36915 - Exact Algorithms and Complexity of the Smallest Grammar Problem Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.32298 - Linear-Time FPT Rectilinear Planarity Testing of Series-Parallel Graphs Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.37018 - An Unconditional Space-Approximation Lower Bound for Semi-Streaming Matching Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.36577 - Text Generation in Low-Resource Languages Using Human-Curated Vocabularies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37105 - RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36878 - Beyond Questions: Evaluating the Stated Knowledge of LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26937 - GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36877 - Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36667 - Scaling Reasoning Efficiently via Relaxed On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11137 - Multi-State Linear Attention with Generalized Second-Order Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37645 - Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07755 - TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36918 - Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37058 - An Embarrassingly Simple Data Selection Strategy for Million-Scale Multi-Modal Instruction-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.13383 - SCOPE: Source Credibility and Outlet Profiling Engine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35929 - API-TAIL: Detecting Model Substitution in LLM APIs through Temperature-Aligned Likelihood Tails Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36801 - Mining the Nineteenth Century for the Thirteenth: Register-Scale Forced Alignment and HTR Bootstrapping via Legacy Regesta and Antiquarian Editions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36956 - Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13776 - Frankly Speaking: The Company Election Integrity Keeps in Congressional Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36187 - Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36109 - CulturalRiddles: A Multicultural Benchmark of Riddles Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29968 - Reinforced Fast Weights via Next-Sequence Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16704 - Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04874 - Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37380 - Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37624 - UCVE: Graph Structured Retrieval for Compliance Validation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37323 - ReCoPII: A Relation-Grounded Framework for Building Contextual PII Masking Datasets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35925 - Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36794 - Every Little Helps: Building Knowledge Graph Foundation Model with Fine-grained Transferable Multi-modal Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15896 - Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08738 - Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37657 - 3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36178 - Annotrace: A Workbench for Step-Level Annotation of Agent Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23284 - Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07853 - Structured Maps for Landmark-Based Route Instructions with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36582 - Detect Before You Disambiguate: Perturbation-Based Input Ambiguity Detection in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36353 - AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06086 - The State and Fate of Multilingual, Contextual Evaluation in the NLP World Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36990 - Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35910 - Benchmarking Task Takeover Across Agent Handoffs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36523 - REGLAT at ArGuard Shared Tasks: An Ensemble-Based Model Integrating NER for Harmful Content Detection in Arabic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37265 - The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03827 - TextCloak: Safeguarding Data from Unauthorized LLM Fine-Tuning via RL-Driven Unlearnable Examples Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28862 - Attention-Graph Curvature for the Verification of Mathematical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16709 - semanticfa: An R Package for Response-Free Semantic Factor Analysis of Psychometric Scales Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37494 - Watermark Basins: Black-Box Detection of Distilled LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37266 - Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37041 - DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07672 - Follow the Gradient: Tracing Safety Degradation Back to Training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37481 - Language Models Keep Abandoned Analyses: Residue and Adaptation after Garden-Path Sentences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36797 - Latent Visual Contrastive Reasoning with Multi-Branch Exploration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36809 - Uncertainty-Guided Multimodal Consensus for Multimodal Sentiment Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.20256 - Self-Regularized Flow Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37115 - Weakness Localization Is Not Enough: State-Aware Recursive Knowledge Improvement for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36811 - Specialization, Diversity, and Scaling in Child-Scale Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36679 - AdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36874 - Hierarchical Low-Rank Reparameterization for Parameter-Efficient Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37068 - Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36538 - Learning to Read Braille: Benchmarking and Improving Braille Recognition Capabilities of VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36195 - OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05843 - Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37037 - The Geometry of Learning: Read-Write Asymmetry Across Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16600 - Nothing Left Behind: Finding Evidence from a Large Randomized Evaluation Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36910 - Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19350 - BanglaBBQ: A Bias Benchmark for Question Answering in the Bangladeshi Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24764 - Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.12868 - CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36734 - Decoupling Consistency and Conflict across MLLM Layers for Fake News Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36569 - Decoupling and Regulating Modality Heads for Fake News Detection under Missing Modality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09711 - Where Does Rhetorical Distortion Live? A Multi-Platform, Multi-Language Measurement of Influencer Content Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26412 - Multi-Label Agreement: A Flexible Framework for Inter-Annotator Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37292 - No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36432 - LLM Hallucination Detection via Low-rank Multilinear Decomposition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36191 - Beyond IceBERT: Open-Data ModernBERT Encoders for Icelandic from 12M to 1B Parameters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36230 - Latent Abstraction for Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17866 - Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37276 - Bridged Self-Distillation for On-Policy Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26397 - AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36493 - Causal Localization of Evidence Effects in Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36524 - V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37019 - Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29927 - Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36184 - Do Language Models Understand Igbo Culture? Beyond Multiple Choice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35168 - PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28363 - Metacognitive Decoding: Efficient Inference for Diffusion Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37642 - Representing the Unseen: Rethinking Visual Imagination for Spatial Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37437 - OmniBrain-0: A Unified Agentic Model for Embodied Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36013 - RoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36533 - Pair Difficulty Matters: Rethinking Pairwise LLM-as-a-Judge Evaluation and Consistency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37577 - Fairness Definitions in Language Models Explained Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.18454 - Balanced State Subspaces for Mamba-2 State Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36617 - EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37609 - Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36948 - Prospector: learning a compact graph traversal policy for scientific reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37121 - Mechanistic Failure Modes of Weight Pruning in Transformer Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37126 - Cross-modal Steering Vectors Exist Across Both Image and Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36269 - Can LLMs Uncover Hidden Physical Laws through Free Exploration? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37649 - Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24585 - Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18420 - LLMs Can Leak Training Data But Do They Want To? Evaluating Memorization Propensity in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06286 - Teach reality, not ethics: a drop-in continued-pretraining corpus installs coupled human-biosphere-AI welfare dispositions across model families Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37484 - How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32055 - What Carries Forward? Pretraining Disclosure Across Language Model Releases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37465 - PRISM-BENCH: Diagnosing Grounded and Faithful Multimodal Reasoning Beyond Final-Answer Accuracy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36554 - Strong Teacher Not Needed? On Distillation in LLM Pretraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23857 - Uncovering Shortcut Amplification in Video RLVR through the Lens of Perceptual Uncertainty Collapse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37211 - EnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37062 - A Unified Approach to Routing and Cascading for LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.10347 - HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36901 - SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13494 - AK_QMUL at ArGuard Shared Tasks: A Single Fine-Tuned JAIS for Arabic Harmful-Prompt Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36360 - Machine learning and digital pragmatics: Which word category influences emoji use most? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21975 - Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36520 - Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17671 - CONCUR: Concordant Auxiliary Rewards for Multi-Task, Multi-Reward Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36437 - DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36929 - Parallel Universes for Temporal Evaluation and Knowledge Updating in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00184 - A Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33036 - Clinical Note Bloat Reduction for Efficient LLM Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16364 - Knowing When to Stop: The Evidence-Action Gap in Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31895 - A Quantitative Approach to Asch Conformity in Frontier Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36668 - A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36449 - EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35290 - ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34717 - MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36006 - Decision Models as Judges for Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37229 - Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37397 - ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37443 - Aligning Large Language Models for Safety in African Languages: A Case Study of Hausa Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37245 - LinMix: Data Mixing as Linear Domain Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37390 - Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36709 - HateSense: Hierarchical Sentiment Analysis Framework for Hate Speech Detection: Implementing Binary and Multiclass Classification Strategy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.05819 - Developing a Speech Language Model for Basque Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36911 - Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32499 - Diagnosing and Mitigating Long-Session Degradation in Full-Duplex Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34991 - A Harness Reducing over-Defensive Writing in Agents by Isolating Objections Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36717 - EmbeddingGemma 2: Unified and Efficient Multimodal Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37364 - Evaluating Geographic Lexical Knowledge in Large Language Models Across 21 Spanish-Speaking Countries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09346 - HEART-Bench: Do LLMs Make Persona-Consistent Decisions? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30058 - Batching the Reflective Optimization Loop: Parallel Proposals Make GEPA Faster and Better Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36774 - Understanding Jev-Style System One Models: Does Structure Reduce Selection Bias? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35826 - Words or Deeds? How LLMs Predict Users' Decisions in Human-Agent Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36813 - SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03620 - FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36083 - FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17399 - AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36980 - Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36202 - Ask Before You Answer: A Question-Driven Evidence Reasoning Architecture (QERA) for In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35083 - How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36082 - JevRec: Linguistic Encoding with Jev-like Decision Modeling for LLM-based Generative Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36937 - DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36759 - Do AI Scientists Know What's New? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36511 - GEPA-Curator: Curated Learning for Self Improving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37651 - Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14141 - ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23813 - Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22506 - FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34889 - Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36805 - Test-Time Communication in Trading Agent Swarms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37448 - Choosing Coding-Agent Benchmarks for Practice: Lessons from Task Demands and Agent Behaviour Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01271 - MedConstBench: Benchmarking How Constitutions Steer LLMs in Medical Ethics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36513 - EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13004 - ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36527 - From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cycle Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.27369 - What Survives Distillation? A Mechanistic Interpretability Study of GPT-2 and DistilGPT-2 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37157 - Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37255 - Don't Pick a Winner: Knowledge Conflicts Need a Prior, Not a Rule Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36169 - Streaming Communication in Multi-Agent Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05158 - SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36384 - ConformalMOS: Uncertainty-Aware MOS Prediction with Conformal Intervals and Ordinal Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36126 - Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18007 - MRI-to-CT Translation of Spinal Images via Anatomy-Guided Pseudo-Pairing and Adversarial Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37134 - A Smart Instant Book Filter Model based on Dual-Objective Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36287 - Verifiable Efficiency Limits of Innate LLM Planning in Sliding Puzzles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36415 - AgentBaton: Efficient Model Collaboration in Agentic Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35959 - An Algebra of Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36795 - GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32596 - When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36849 - A Lightweight Attention-Based CNN with Saliency-Map Interpretability for Skin Cancer Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37314 - Diversity Combining for Multi-Path LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38829 - Learning to Look Beyond Screens: Transferable Visual Observation from GUI Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37093 - Detailed balance in large language model-driven agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10047 - The View from Nowhere: Population-Centered Agent Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36660 - Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36932 - Evaluating Visual Language Models on Visual Grounding for Visually Impaired People Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33078 - NxN E-valuation: Hypothesis Certification via a Conformal CRT Null Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06621 - When to Intervene? An Empirical Study of Errors and Self-Recovery in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36471 - Directional Statistics on Circles and Spheres: A New Angle on Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36227 - DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.17098 - The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27895 - Tap2Listen: Instant Target Switching for Streaming Audio-Visual Speaker Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36643 - Waypoint: Analytically Modeling GEMM for CPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34914 - Strategyproof Deep Reinforcement Learning for Online Resource Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37504 - RPSD: Retrieval-Privileged On-Policy Self-Distillation with Optimal Transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37281 - Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36329 - Dream-COP: Guiding Algorithm Discovery for Combinatorial Optimization Problems in an Experience World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36618 - Robust LLM Data Selection via Content-Invariant Gradient Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36755 - LiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37166 - Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36204 - Polarity--Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36625 - The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35541 - Pricing Cross-Bank Context in Federated Anti-Money Laundering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35996 - Dirichlet Process Mixtures within Semiparametric Bayesian Networks: A Novel Conditional Density Estimation Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36110 - Counting the Bandages: On measuring the time that AI saves Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35942 - Silent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34817 - CalArena: A Large-Scale Post-Hoc Calibration Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30188 - Tailored to you: longitudinal effects of personalising language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20077 - LoRA on a Budget: Function-Aware Post-Hoc Compression for Adapter Fleets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36386 - Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36584 - From Language to Navigation Goals: A Vision-Language Approach for Semantic Navigation of Mobile Robots Using RGB-D Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13624 - PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37471 - MARQ: A Modular, LLM-Agnostic Requirement Quality Assessor Infused with Systems Engineering Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36234 - Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36108 - CoS-VQ: Coordinated Shared-Scale Vector Quantization for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37336 - SemLoc: Structured Grounding of Free-Form LLM Reasoning for Fault Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29109 - Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36767 - The uneven rise of AI-generated web content Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36631 - How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36328 - Who Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35930 - What the Primary Lund Plane Omits: A Model-Stitching Diagnosis of a Jet-Tagger Representation Gap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37137 - REALM: Retrospective Encoder Alignment for LFP Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14867 - When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37239 - GCSR-OCC: Geometry Calibration and Semantic Routing for Open-Vocabulary Occupancy Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37149 - Full Collapse Is Suboptimal: Controlled Partial Neural Collapse for Long-Tailed Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36460 - SetGRPO: Calibrating Grader-Induced Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36807 - CASEL: Consequence-Aware Selective Execution for Reliable Long-Horizon Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36570 - ADTGuard: Adaptive Depth-Time Safeguard for Streaming Inference in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36574 - 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 - Dependency Graphs of Mathematical Arguments: Representation, Structural Measurement, and Proof Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36776 - From Interaction to Capability: Task Advancement as State and Supervision for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37482 - Learning to Formalize: Bridging Open-Ended Workloads and Fast Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36595 - Concordat: Typed Sessions for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37461 - Natural Hard-Negative Mining from Positives for Instruction-Following Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.36900 - The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36077 - Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37393 - Ctrl-A: Control-Driven Machine Learning using Adaptive Online Data Augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21819 - A Computationally Efficient Multi-Section Whole Slide Image Analysis for Capturing Prostate Cancer Multifocality in Biochemical Recurrence Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20273 - Vision-Language Agents Can Learn in Their Own Latent Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36925 - HOLogicBench: Evaluating Higher-Order Logical Reasoning in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23238 - From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36146 - Memorilla: Latent Semantic Memory for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21375 - Suan: Rectifying Direct Preference Safety Alignment in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08634 - Autonomous fixed-wing interception using reinforcement learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37470 - InfraDev: Can Coding Agents Develop AI Infrastructure, and How Can We Tell? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36589 - Do Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36015 - CLEAR: Coupling Local Evidence with Affective Representations for Multimodal Emotion Recognition in Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18547 - TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37571 - Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35982 - Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36624 - GraphRAGProv: GraphRAG Meets How-Provenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37237 - MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17169 - Inferring Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.03186 - Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37386 - ResCom: Activation Residual Compensation for Large Language Model Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35955 - Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36888 - HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36374 - AI-guided deep visual proteomics reveals recurrence-associated morpho-molecular signatures within triple-negative breast cancers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03145 - Replication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36151 - HiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19846 - Making Self-Driving Laboratories Auditable:A Unified Framework for Hybrid Actions,Measurements, and Safe Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36761 - Evolving Agent Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36848 - RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36444 - Edge-AI-Driven Learning-to-Rank for Decentralized Task Allocation in Circular Smart Manufacturing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16433 - Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33767 - Understanding the limits of latent world models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37588 - Spine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37224 - FIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36476 - Hidden-State Privacy Has an Empty Middle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24042 - How Reliable Is Individualized Functional-Network Attribution in Resting-State fMRI Cognitive Prediction in ADNI? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37472 - WCC: A Learning-Based Framework for Deciding When to Apply Cooperative Coevolution in Large-Scale Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37329 - When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36826 - GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37545 - Rethinking Multi-View Fusion for Urban Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31850 - Less is more: learning what to profile for GPU kernel optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36576 - Skill Dreaming: Evolving Repository Skills through Pull Request Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36188 - Crop Yield Prediction Using Regression Models: A Comparative Evaluation of Model Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37022 - One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: A Controlled Comparison of an Iterative Neural Minimizer, Set Transformers and Classical Estimators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03614 - MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07328 - Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36671 - Beyond Greenwashing: Algorithmic Resilience and the Non-Linear Governance Premium in Sovereign Capital Flows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35895 - Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07063 - Ontology-guided multi-agent reasoning for explainable differential diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36325 - VideoLVR: Latent Visual Reasoning over Grounded Video Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37613 - The Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03222 - When Retrieval Is Not Enough: Obsolete Facts in Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.36308 - LearnPrunerV2: Learnable Progressive Token Pruning for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36986 - The Theory of Strategic Evolution: Three Principles of Strategic Replicators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07901 - Aligning Institutional Power and Operational Ability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37342 - Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35595 - kw-bench: Breaking Frontier Harnesses on Real-World Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36405 - Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36192 - Data-Driven Maintenance Optimization: Aligning Prognostic Learning with Decision Objective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19698 - Does Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37201 - Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36341 - Learning response-aware patient dynamics for respiratory support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32782 - Atom as an Agent: Emergent Order by Collective Predictive Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36673 - PsyJev: Psychological Analysis via System-1 Judgment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36689 - ReForest: Interpretability Meets Reasoning in Isolation Forest Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37316 - Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37668 - KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37655 - ATEMPO: Amortized Transfer Entropy Model Per-lag Over-Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36536 - An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36820 - Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37405 - Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36764 - Smart Surveillance: Deep Learning and Hybrid Approaches for Dynamic Scene Analysis, Object Detection and Motion Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.05331 - A First-Step Bias Restores Lost Diversity in Diffusion Model Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37110 - Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36951 - Towards Human-AI Complementarity for AI Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24969 - Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37139 - CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36100 - Foreground-Aware Dataset Distillation via Dual-Path Patch Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02727 - AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23018 - Bayes-Adaptive MDPs for Rollout Allocation to Enhance GRPO Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37429 - Your Agent Acts Differently When You're Around: How User Presence Changes Agent Behavior in Negotiation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36435 - Correcting Before Adapting: Gradient Correction for Federated Adaptive Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.02727 - GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37598 - cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36250 - CrowdCC: Jointly Benchmarking Corruption Robustness and Deployment Quantization in Crowd Counting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36340 - SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15401 - Reach-Avoid Differential game with Reachability Analysis for UAVs: A decomposition approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22793 - When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18740 - HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36696 - AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.09254 - count-catcher: Lean Theorems from Model Counting Certificates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36196 - From Deterministic to Generative Deep Learning for Urban Air Quality Reconstruction from Sparse Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25687 - REACH: An RL-based Hierarchical Humanoid Crawling Framework for Adaptable Confined Space Traversal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36546 - Layerwise Repacking: Variable-Length Hybrid-Attention Training without an Extra Redistribution Pass Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35989 - FeatureArc: Benchmarking Coding Agents on Evolving Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37434 - Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01487 - HGPRGDel: GPR-Aware Learning and Ranking for Growth-Coupled Gene Deletion Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37478 - A Hyper-Logical View on Multi-Agent Path Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35964 - UnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35980 - FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36545 - SQuID: A Benchmark for Quantitative Spatial Reasoning on Satellite Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13401 - M4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37459 - TCM-DiagCommit: A TCM-SD-Derived Benchmark for Evidence-Conditioned Syndrome Selection and Commitment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37243 - On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07860 - Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37656 - TOPS: Reshaping Flow Source and Transport for Multi-Task Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36694 - Stratum: Repository Memory for Coding Agents Beyond the Context Window Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36153 - Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17709 - The Structure Gap: When More Data Cannot Replace Structured Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37523 - Can AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36185 - Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37375 - VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34717 - ScalableRAG: High-Quality RAG with Exact Corpus Operations at Minimal Ingestion Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25135 - Why and How to Do Science When AI Is Better at It: A Framework Grounded in Human Understanding and Direction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36116 - OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37081 - Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37567 - Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36247 - Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21628 - Physical structure as an organizing principle for universal Hamiltonian learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36135 - ActiveAlign: Aligning Egocentric Manipulation via Active Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36859 - Blindfold: Keeping the Audit Coin Secret from LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37055 - God Does Not Play Dice: Enforcing Batch Invariance in Agentic Kernel Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36623 - Evaluating Priority Dispatch for Premium Membership in On-demand Taxi-sharing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37011 - Action-Value Calibration via Continuation Sharing for Long-Horizon Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37195 - Advancement or Acceleration? How Data Curation Improves LLM Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36983 - Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03385 - WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37161 - Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36183 - ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37666 - Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36114 - I-HITL: Inalienable Human-in-the-Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35835 - DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36950 - Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00711 - ASTROLABE: A 3D Particle-Level Surrogate for Cosmology Simulation with Physical Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27068 - ProCerDCL: Query-Efficient Black-Box Probabilistic Verification of Deep Learning Compiler Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36499 - MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06745 - Difficulty-Estimated Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06375 - Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37242 - Let the Gate Decide: Per-Lookup Precision for Quantized Conditional Memory in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35985 - Seeing the Options: Typed Decisions over Visual Candidates with Reusable Option Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33702 - DuplexTune: Coupled-State Replay for Memory-Efficient Mixture-of-Experts Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36009 - Preconditioned Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02337 - Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03918 - Efficient Token-Level Policy Optimization for Masked Diffusion Models via Velocity Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01563 - MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37599 - Moderation by Interrogation: Uncovering Concealed Intent in Agent Social Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12856 - EMMA: Structured Episodic Memory for Multi-Agent Workflow Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35966 - ARCANA: A Benchmark for Abstraction and Analogical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29271 - Reliability-Aware Short-Term Glycemic Risk Prediction Using an Anchor-Based Comparative Framework of Sequence, Multimodal, and State-Updating Digital-Twin Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36363 - MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37175 - Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37070 - Distilling Metacognitive Behaviors through Agentic Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22508 - AI-Assisted Discovery of CNOT Decompositions for Quantum Permutations on Constrained Topologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37045 - Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00391 - From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36713 - Rollback: Experience Backtracking in World Models for Policy Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36068 - From SGD to Muon: Adaptive Optimization via Schatten-p Norms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19781 - Learning Where to Trust: Reliability-Guided Expert Routing and Velocity Gating for 3D Deformable Registration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36672 - Structured Time-Frequency Representation for Channel Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35956 - CIVER: Causal Intervention Verification for Reliable Code Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36010 - JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35532 - LM-DSB: A Lightweight Multi-agent System for Automated Daily Safety Bulletin Generation in Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36433 - Beyond the Readout: A Latent Numerical Frame Shared Across Modality and Operation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37422 - Remembering Is Not Enough: Refining Memories and Learning When to Use Them in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36652 - PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31810 - Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37145 - Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36113 - BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17000 - MIDAS: Mosaic Input-Specific Differentiable Architecture Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17700 - Correction or Manipulation? Measuring Epistemic Vigilance in LLM Agents Under User Pressure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36453 - TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15773 - Follow the Herd: A Data-Driven Approach for Actionable Recourse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36580 - Interpretable Deep Learning Models for Breast Cancer Diagnosis Using Medical Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37026 - DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05758 - Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36298 - Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37550 - LociArt: A Unified Paradigm for Free-Style Local Video Stylization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36456 - Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35984 - A swap-adversarial framework for domain generalization in pre- and post-stimulation Parkinsonian state classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10528 - Multiple Leak Localization in Water Distribution Networks through Graph Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35972 - Beyond Answer Changes: Matched Same-Class Controls for Local Audio Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37605 - DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15796 - Enhancing Clinical Classifier Robustness with Deep Representation Learning Based OOD Detection on DNA Methylation Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36344 - AOS-Bench: Can LLM Agents Manage Dynamic Workloads? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33178 - Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14708 - Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03445 - Structure, Not Sequence: Tracking and Validating Folding Mechanisms in ESMFold's Trunk with Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36226 - Detecting and Mitigating Query-Based System Prompt Leakage Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36295 - Do bots feel bad? Assessing empirical evidence for functional valence in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36962 - Orthogonal and Parametrized Multi-Attribute Steering of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37517 - From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36445 - R\`enyi-Regularized Flow-Based Variational Inference for Bayesian Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37169 - Timestral Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37585 - DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22688 - Conservative Dueling Bandits: Preference Learning under Baseline Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36708 - scPyviewer: a Python-native interactive viewer from AnnData single-cell data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35890 - BUSTA: Teaching Small Language Models to Reason About Binary Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36288 - From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28160 - Posterior-First Neural PDE Simulation: Inferring What Downstream Tasks Need from a Single Field Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03247 - Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12401 - When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37547 - Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37533 - NextEval: An Agent-Based Solver and Benchmark for Derivative-Free Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36553 - Expert lithological labels do not improve learning when used to predict marine sediment properties Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36410 - LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19358 - TAPESTRY: A Single Backbone for Video Generation and Robot Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36823 - When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12718 - Hardware-Matched Spiking Neural Networks for Real-Time Purkinje Cell Spike Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37104 - Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02343 - First-Order LoRA Training with Phone NPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24816 - From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27860 - Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.20729 - RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09410 - Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37407 - Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37369 - Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37215 - Can LLMs Design Video Coding Tools? A Case Study on Planar Mode Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01535 - She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.18524 - PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11225 - Proactive Memory for Event-Driven LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36967 - Actionable CBFI: Prescriptive Interventional Diagnosis and Interaction-Aware Escalation for Sparse Causal Algorithmic Recourse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27821 - Doubly Robust Alignment for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.01183 - CogArena: Benchmarking Multimodal Agents on Interactive Behavioral Experiments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36484 - Proposing Better Rollouts for On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36477 - On the Reliability and Stability of Selective Methods in Malware Classification Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22843 - Optimal Experiments for Partial Causal Effect Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06993 - In-Context Learning for MIMO Turbo Receivers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.06175 - PolicyMediator: Multi-Regional Policy Learning through Mediation Agents with Evolving Skills in OPC Ecosystems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35997 - SFE-O: An Ontology for Knowledge-Grounded AI in Supercritical CO$_2$ Biomass Extraction and Fractionation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37123 - LLM Code Smells: A Taxonomy and Detection Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22976 - What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37631 - Epsilon-Identifiability of Causal Quantities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2301.12022 - MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37647 - MM-Net: A Multimodal Multi-Task Network for Sleep Staging and Sleep Apnea Assessment After Ischemic Stroke Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36583 - Fig: Automated Multiagent Behavior Elicitor Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28891 - Agent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36229 - On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02141 - Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36824 - Experience Memory Graph: Extracting Reusable Correction Knowledge from Agent Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13884 - Conservative Policy Iteration For Zero-Sum POSGs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36847 - Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35905 - How K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10780 - Repulsive Population Policy Gradients for Behaviorally Diverse Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36425 - PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35987 - Trust Region Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04751 - What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07687 - Semantic World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19818 - AnalogScout: Simulation-Efficient PVT-Aware Analog Sizing with LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37319 - Generative Refinement Learning for Temporal Interpolation in Scientific Machine Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36751 - Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36947 - LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17123 - AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22724 - When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37561 - VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00122 - Curriculum-Driven Deep Reinforcement Learning for Autonomous Far-Range Rocket Landing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35954 - Provenance-Aware Belief Updating in Human-AI Feedback Loops Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13008 - WAKMan: Workload Aware KVCache Manager Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36355 - The Price of Failure Risk: Clipped Barrier Policy Gradients with Convex Regularization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.19193 - OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36335 - Legislating World-Model-Based Planning with Legal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15113 - From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12443 - JEPA-Inspired Latent Field Prediction for Sparse-Pilot MIMO-OFDM Channel Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37391 ## Community - Quoting Ted Sanders Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/28/ted-sanders/ - GitHub Octoverse 2026 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/28/github-octoverse-2026/ - The October inflection point for vibe game development Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/28/vibe-game-development/ - Fragments: October 28 Source: martin-fowler Topic: Architecture (+AI) URL: https://martinfowler.com/fragments/2026-10-28.html - Quoting Terk Terkowitz Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/28/terk-terkowitz/ - Igor Suhorukov: Which language should an AI agent use to search its memory: SQL or SPARQL? Source: planet-postgresql Topic: PostgreSQL (+AI) URL: https://postgr.es/p/9Al - Gemini 4 Carbon Source: hacker-news Topic: General (+AI) URL: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/ - Nvidia Nemotron 3.5 Transcribe: open ASR for 40 languages Source: hacker-news Topic: General (+AI) URL: https://huggingface.co/blog/nvidia/nemotron-transcribe-granary - Anthropic now lets Claude users jump out of plane without parachute Source: hacker-news Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/27/anthropic-now-lets-claude-users-jump-out-of-plane-without-parachute/5305807 - Sleep framework: A new way for LLMs to retain knowledge in continual learning Source: hacker-news Topic: General (+AI) URL: https://research.google/blog/the-sleep-framework-a-new-way-for-llms-to-retain-knowledge-in-continual-learning/ - The Benchmarking Crisis Source: lobsters Topic: General (+AI, Databases) URL: http://databasearchitects.blogspot.com/2026/10/the-benchmarking-crisis.html ## Media - AI agent memory Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/tarq5cgw7PE - Why AI agents need their own identity & audit trails Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/ITmbZFFGQuI - Introducing the TPU agent suite (preview): Open source agents for PyTorch on Cloud TPU Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=hK3xqW_HrP0