TILens Daily Edition 2026-10-21 Filters: topic=ai, github=hidden Stats: 662 articles, 28 sources, 615 research papers Top topics: AI, AI Research, Information Retrieval ## News - Broad access through consistent standards Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/broad-access-through-consistent-standards - NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/nvidia/kumo-relational - How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/Dharma-AI/vocabx-vocabulary-specialization - How AT&T is rethinking in-house legal work with OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/att-legal - Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium. Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/amazon/profiling-torchneuron-part-1 - AWS Neuron 2.33 adds native PyTorch support, Neuron Observer, and other new features Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/aws-announce-neuron-2-33-0 - Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/ibm-granite/granite-speech-5 - ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/chatgpt-ads-expands-26-new-countries - NVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and Interpretability Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/nvidia/kumo-forecast - OpenAI models are coming to Google Cloud Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/openai-models-google-cloud - Amazon SageMaker AI now supports custom sequence lengths for serverless model customization jobs Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/sagemaker-custom-sequence-lengths/ - How we built ChatGPT’s novel ad stack for user trust and relevance Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/building-chatgpt-ad-stack - Patch the Planet: global response coordination as agents uncover critical vulnerabilities Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/coordinated-disclosure-of-critical-vulnerabilities - Using thousands of AI agents to uncover new leads in biological data Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/scaling-ai-research-for-complex-biological-data - Democratic governance of frontier AI, part II: Empowering cyber defenders Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/empowering-cyber-defenders - Cloudflare links vulnerability discovery to defense with OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/cloudflare-cyber - Amodei says Anthropic’s safety delay may have cost it an AI lead Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/anthropic-mythos-safety-pace/ - Zapier: Clean the Email With a Code Step Before ChatGPT Sees It (Quoted Threads, Signatures, First Names) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/robert_breen_d96e41ecd765/zapier-clean-the-email-with-a-code-step-before-chatgpt-sees-it-quoted-threads-signatures-first-3oce - 😸 WATCH: Can Living Neurons Make AI 5x Faster? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/watch-can-living-neurons-make-ai-5x-faster/ - Nvidia woos wary Europeans with more open weights models Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/21/nvidia-woos-wary-europeans-with-more-open-weights-models/5304552 - OpenAI's latest AI models are coming to Google Cloud and Antigravity Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/10/openais-latest-ai-models-are-coming-to-google-cloud-and-antigravity/ - PHP Armageddon: OpenAI, Google’s Wiz find ancient holes, panicking the internet Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/21/php-armageddon-openai-googles-wiz-find-ancient-holes-panicking-the-internet/ - LLM Prompt Caching Versus Semantic Caching Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/llm-prompt-caching-versus-semantic - Sam Altman’s three endings for the AI safety race Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/sam-altman-three-endings-for-the-ai-safety-race - 😺 Meta’s Muse made shared chats searchable Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-s-muse-made-shared-chats-searchable-a190/ - I built 59 free browser-based dev tools in vanilla JS — here's what I learned Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/yuvaraj_radhakrishnan_224/i-built-59-free-browser-based-dev-tools-in-vanilla-js-heres-what-i-learned-1bd4 - Better Loading States for AI Apps Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/vectorchi/better-loading-states-for-ai-apps-3f0i - Everything That Happened in AI Today (Wednesday, October 21, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-october-21-2026/ - Could AI Models Be Easier to Understand Than Scientists Thought? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/could-ai-models-be-easier-to-understand-than-scientists-thought/ - Who Should Have the Power to Stop a Dangerous AI Model? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/who-should-have-the-power-to-stop-a-dangerous-ai-model/ - Anthropic S-1 leaks 💰, Tesla SpaceX merger talks 🚀, increase your slope 📈 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-10-21 ## Research - Empowering frontline maternal care with AI-assisted ultrasound Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/empowering-frontline-maternal-care-with-ai-assisted-ultrasound/ - Decision Models in Action: Build a Hybrid LLM Workflow Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/decision-models-in-action-build-a-hybrid-llm-workflow/ - How to Turn Long-Running Python Simulations Into a Self-Service Platform Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-turn-long-running-python-simulations-into-a-self-service-platform/ - Spatial Reasoning in AI Models, Taken Apart Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/spatial-reasoning-in-ai-models-taken-apart/ - I Built a Pipeline to Track the Job Market I'm Trying to Break Into. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-built-a-pipeline-to-track-the-job-market-im-trying-to-break-into/ - Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27468 - LEAF: LUT-aware Efficient Attention on FPGAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27078 - MemT-1.0: Towards Memory-Native Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26825 - ClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27079 - Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28355 - The price of multi-group transductive learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04423 - Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.14102 - When Does Training on Synthetic Data Provably Work? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28036 - Stabilizing Filters for Graph Signal Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28318 - Scaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27439 - TTS-Q: Speaker-Aware Post-Training Quantization of Text-to-Speech Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12474 - BCT: Bayes-Consistent Tempering for Flow Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27641 - Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and Resampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28294 - Neural Operator Splitting for Fluid Dynamics in Complex Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27671 - Optimal L2 Regularization in High-dimensional Continual Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13844 - MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15235 - Elicitation or Expansion? Demystifying Gains from Agent Harness Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27889 - When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27714 - Robust Lightweight IoT Device Fingerprinting Under Network Traffic Anomalies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27351 - Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27473 - Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client Outages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28545 - Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27443 - Learned Readout Tokens for Extracting Large Language Model Confidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27566 - Guided Diffusion for Trustworthy Synthetic Text Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27259 - MultiCard: Multiple Attribute Cardinality Estimation via Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2610.27019 - MuPACE: Learning to Pace Muon for LoRA Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.28072 - Auditing Safety Preference Supervision with Recorded Derivations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27266 - LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27100 - Bayesian Nonparametric Dynamical Clustering of Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06919 - Measuring, Localizing, and Ablating Alignment Signatures in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30526 - Decision Sufficiency of Learned Representation Interfaces for Safe Generative Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27446 - VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27280 - ICLHerd: Herding-Based Data Selection for LLMs with In-Context Learning as a Proxy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27142 - Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27870 - Poisoning-Based Backdoors Are Not Cryptographic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28045 - BEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27542 - Knowledge That Is Linear Before Fine-Tuning Generalizes After It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22300 - Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28632 - Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28935 - Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28315 - EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04953 - Service-Induced Congestion in Memory-Constrained LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15555 - Lower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low Curvature Trace Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27550 - FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09250 - Feature Selection for Latent Factor Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.10128 - Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28567 - Neural Closed-Loop Identification of Nonlinear Systems with Stability and Generalization Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27970 - This is SParTA: A modular, efficient and scalable transformer architecture for jet-tagging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27106 - Claims of emergence in AI should be grounded in information decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28479 - Blending data and physics for reduced-order modeling of systems with spatiotemporal chaotic dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21299 - From Generic to Dedicated: A Novel Optimizer for Online Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27835 - Robust Latent Variable Graphical Models: Exact Recovery and Fundamental Limits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27010 - FLEXI-Haz: Semiparametric Deep Survival Inference Beyond Proportional Hazards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10570 - QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33848 - Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26772 - HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27561 - Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00362 - Does On-Policy Distillation Need to Complete Every Rollout? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21337 - Sample-efficient learning with Dense Associative Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27384 - The Shape of Wisdom: How Language Models Converge on an Answer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01202 - Turning TS2Vec into a Foundation Model for Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28602 - Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04987 - SafeExplorer: An Unbiased Mixed-Policy Gradient for Reinforcement Learning with Recovery Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08925 - Planning under Noise with Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28623 - When Parameter Gradient Flows Close in Representation Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27474 - SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27812 - ProVe: Proposer-Verifier Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27815 - Learning-Theoretic Foundation for General Coded Computing: The Adversarial Setting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27440 - Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and Remedies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23716 - A Jointly Efficient and Near-Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10971 - $S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37976 - Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08541 - Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28628 - CorteXforge: Scenario-Based RF Dataset Generation on Real Testbeds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26999 - Deep learning-based multi-level airway collapse site localization on obstructive sleep apnea patients based on snoring sounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.16030 - Wasserstein Robust Classification Error: Surrogate Loss Misalignment and Distributional Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10000 - Geometry-Aware Block Selection for Sparse Variational Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28256 - TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28229 - Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28495 - Baseline and Incremental: User, Item, and Request Debiasing in Instagram Feed Ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27423 - Learning Administrative Boundary-Aware Location Encoders via Reverse Geocoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24306 - Soliton Profiles in 1D: Enhanced Neural-Network Solvers and Constrained Deep Ritz Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27500 - Self-Evolving Agents through Privileged Retrospective Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27495 - Relative Representations Enable Portable White-Box Monitoring Across Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28366 - Identifying Dependent Components from Multi-domain Linear Mixtures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28330 - Auditing the Product, Not the Recursion: The Evaluation Evidence Behind Recursive Self-Improvement Claims Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27610 - Unsupervised Head Network Personalization for Split Computing via Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27952 - AC/DC on a Budget - Alternating Sparse Phases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27758 - Evaluating utility of clinical prediction models: A comparison of decision curve analysis and cost curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24608 - From Outcomes to Steps: Reliable Success-Aware Critic Learning for Long-Horizon Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27623 - Asymmetric Bidirectional Predictive Dynamics in Google Search and COVID-19 Time Series: A Multi-Horizon Forecast-Error Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28563 - H2DF: Calibrated Target Bands for Controllable Language-Model Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26864 - When Weak Submodularity Meets Matroids: How Does Standard Greedy Behave? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26967 - NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23271 - From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27863 - Give the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27756 - Quantifying the Threat: A Bayesian Probabilistic Framework for Heavy Metal Health Risks among Children in the Densu Basin, Ghana Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28064 - A Simple and General Approach to top-$k$ Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26407 - Learn from Your Mistakes: Self-Correcting Masked Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11590 - Binary Agreement for Efficient Unsupervised Confidence Calibration of Reasoning LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.19444 - EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26039 - V-CoLA: Vision Token Compression with Linear Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11251 - Hilbert-Scale Stability of Posterior Diffusion Priors for Ill-Posed Signal Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27030 - OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13003 - StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15816 - When Momentum Helps Polyak--Ruppert Averaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27990 - Steering intonational tunes in text-to-speech synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27403 - The Dynamics of Collapse and Recovery in Clustered Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28565 - ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27046 - Characterizing Cross-Relay Generalization Failure in Machine Learning-Based Power System Protection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28348 - Simpler Logarithmic Approximation Algorithms for the Optimal Decision Tree and Adaptive Set Cover Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12036 - WeAct: Dynamic Weight Switching as Agent Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26847 - Representing short-term movement to reveal animal identity and learning progress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27140 - PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18587 - COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11165 - Training-Free On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22236 - Tensor computing application programming interface: An application-oriented, lightweight API for portable high-performance tensor network computations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23917 - Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28427 - Neighborhood-Aware Unlearning for Generative Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27232 - DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG seizure-related Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11578 - Accelerating Optimization via Differentiable Stopping Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22509 - Ask to Learn: Query-Based Collaborative Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27606 - FoundPDE: A generative foundation model for data-driven symbolic discovery of partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26963 - What Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32002 - Weak-$L^\alpha$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy Tails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28107 - PULSE: Personalized Opportunistic Learning for Wearable Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28081 - A Hybrid TFT-NBEATS Framework for Robust Multi-Horizon Photovoltaic Power Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27155 - PaPi: Parallel Picard-Duhamel Integration for Fast Neuro-Spectral Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28591 - CyberHull: Deterministic Malicious URL Isolation via Convex Hull Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27675 - Trail-Weighted Influence Scores for Approximate Outcome Prediction in Bayesian Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27366 - Observation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28327 - Interpretable PM2.5 Forecasting for Urban Air Quality: A Comparative Study of Adaptive Time-Series Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25495 - The Reward Model Selection Crisis in Personalized Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23067 - Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26030 - TRCM: Topology-Aware Route-Consistency Modeling for Robust Neural Vehicle Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27568 - Federated Learning: From Theory to Practice Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19183 - BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28500 - Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21669 - Fixed Sets and the Hardness of Computing Correlated Equilibria Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28141 - Auditing Where Concept Bottleneck Accuracy Comes From on CUB Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28059 - Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive Radars Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27585 - RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05616 - Towards Hyperparameter Transfer for Differentially Private Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22976 - Rethinking Generalization in Knowledge Graph Embedding: An Empirical Study and Sparse Peak Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23442 - What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27534 - Selecting the Best Few with Human Evaluators: Adaptively Combining Ratings and Pairwise Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26380 - Reliable Estimation of Differential Privacy under Selection Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27021 - TreeWalker: Partial Evaluation for Grouped Tree-Ensemble Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03939 - CFR without Unbiasedness: Debit-Budgeted Public Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14761 - Automated Brick Schema Knowledge Graph Completion Across Buildings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27339 - Timing-Aware and Interpretable Self-Attention for Event-Based Wearable Task Transition Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27549 - Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28580 - Offline Makes Online Better: Calibrated Cache Compression for Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28192 - Help Me Help You: The Aggregate Value of Source and Target Data in Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.16189 - The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28576 - CountVideoBench: A Benchmark to Evaluate Prediction Biases on the Object Counting task by Video-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28356 - Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27364 - Simulating, Fast and Slow: Learning Policies for Black-Box Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.04261 - Certified Adaptive List Decoding for Error-Correcting Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27805 - The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19616 - Federated learning with heavy-tailed gradient noise and communication noise: a variance-reduction based algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22466 - Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28411 - Convergent Performance, Divergent Mechanisms in LoRA-Adapted Vision Foundation Models for Brain MRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28255 - Learning global river system hydrodynamics with a topology-informed foundation model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22293 - Hybrid Belief Reinforcement Learning for Efficient Coordinated Spatial Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03595 - Foundations of the Scaling Law Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27789 - Understanding the Benefits of Scaffolds through Computational Separations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27157 - Latent Projection for Latent Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26979 - PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.18462 - Learning Reachability-Based Safety Representations for Real-Time Robot Navigation in Unknown and Dynamic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16522 - Decomposing Refusal Steering in Mixture-of-Experts Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04160 - A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19083 - Pairwise Learning Increases Data Efficiency in Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27669 - Understanding Data Augmentation under Label Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27701 - Gaussian Approximation of Besov Functions for Logistic Classification on Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27022 - STRABLE: Benchmarking Tabular Machine Learning with Strings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12292 - ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26929 - Covariance-Aware Transformers for Quadratic Programming and Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14506 - Learning Computational Structure for Sample-Efficient Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28555 - Abstract Compression of Conversational Audio Context for LLM-based ASR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26246 - Truthful Calibration Measures for Sequential Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21348 - When does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09496 - A Likely Geometry of Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.26266 - Multi-Objective Evolutionary Semi-Supervised Learning for Resource-Aware Smart City Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27703 - On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18727 - Some remarks on the connection between generative diffusion and optimal transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13614 - ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35954 - ABACUS: A Benchmark for Image Editing Models to Assess Object Category and Counting Under Scene Conservation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28316 - Compute-Optimal Scaling Laws for Spiking Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15146 - When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27573 - Adaptive Pullback: Reweighting Supervision at Penalty Jumps in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28194 - Hybrid Momentum Methods for Optimizing Deep Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27674 - Process-Aware Event Log Augmentation for Process Prediction under Labeled Data Scarcity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24777 - LatticeMind: A Validation-Gated Agentic Framework for Density Functional Theory Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26869 - Measuring Variable Importance Using Proportional Inclusive Marginal Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17053 - BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03759 - You Are the Trigger: Speaker-Activated Backdoors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27210 - When Do LLMs Help with Feature Selection? A Systematic Empirical Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28556 - Two $\operatorname{ReLU}$ Layers is All You Need Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28587 - Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27763 - Sensitivity-Orthogonal Residual Learning for Adaptive Sideslip and Cornering Stiffness Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27586 - Scalable Posterior Uncertainty for Flexible Density-Based Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03188 - Half-Truths Break Similarity-Based Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23906 - Inferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27668 - Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18036 - Expert-Guided Rubrics as Dense Reward Signals for Reinforcement Learning in Non-Verifiable Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26932 - FERPO: Forward Entropy-Regularized Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02198 - Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08365 - CUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27645 - RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27107 - Dynamic Dual-Feedback Conformal Inference for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26987 - The Router Already Knows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27421 - Polynomial Learning of Positive ReLU Networks under Gaussian Inputs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25116 - Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27180 - What Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27277 - Parameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28200 - Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.11228 - Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00661 - TerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27793 - Confessions of a Masked MDP Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28360 - The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27895 - Using Data-Derived Priors to Guide CNN Architecture Design for NIR Chemometrics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25636 - DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28419 - Convergence of stochastic gradient descent for learning linear neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28561 - LLMs are Brittle to Simple Code Transformations: Introducing CETBench - A Benchmark for Code-Equivalence Checking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.04019 - DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23047 - KuaFu: Compressing Long User Behavior into Understanding at Billion Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31045 - LocaLeJEPA: Maximum Entropy Representations under Geometric Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28458 - Influence Is the Target-Response Jacobian Times Residuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27689 - Text-to-Image Generative Modeling Without Language Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26863 - Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22887 - Beyond Policy Discrepancy: Capability-Aware Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26950 - Training Controllable World Models via Action Influence Maximization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27387 - Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27580 - Communication Complexity of Universal Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27402 - Universal Online Convex Optimization With Delayed Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28058 - LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27444 - Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18280 - Fixed-Size Active Statistical Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27389 - AURA: Angular Update Rate Adaptation for training complex-valued neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25914 - A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22341 - Taskonomy: Disentangling Task Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1804.08328 - Quadratic Sample Complexity for Strictly Replicable Realizable Learning with Unknown Marginals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26944 - Physics-Inspired Optimizers beyond the Edge of Stability: Period-Two Orbits and Delayed Instability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27321 - What Survives When Activation Steering Is Used as Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14958 - From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28160 - LLM-Attack Suite: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22722 - Complete or Sparse: A Tale of Two Identifiabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20851 - Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27141 - FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.13925 - Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27490 - Learning the Geometry of Materials Space with Trained Neural Tangent Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27412 - Privacy Accounting for Empirical Denoisers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27710 - Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29515 - Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22908 - Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21403 - Graph Neural Networks for Astrophysics and Cosmology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27051 - A latent control model for realistic rodent motion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27279 - DeliMF: Gated Cross-Attention Fusion of Structured Time Series and Clinical Text for Early Intensive Care Delirium Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24585 - Causal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28134 - Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23239 - Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26443 - Learning Normal Coordinates on Riemannian Manifolds with Flow Charts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28302 - Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28286 - HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26770 - ARISE: An adaptive residual-informed stability ensemble for feature selection in small-sample biomedical omics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14866 - Deficit-Driven Stratified Acquisition for Building STRATA-S12: An Open SAR-Optical Corpus for Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17680 - Reframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28197 - Predicting silent failures of learned inference under restricted access: what measurement physics and prior information explain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28155 - Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27206 - Tensor Cookbook: Mastering Tensors through Diagrams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16610 - The surprising simplicity of forecasting quantum chaotic many-body dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10697 - Projected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27467 - Loopy: Low-Bit Quantization Framework for Looped Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05265 - When Dynamic Scaling Fails: A Scale-State Feedback Governs Recurrent-State Quantization in Linear-Attention and SSM LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15139 - CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26923 - A Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23185 - Decentralized Optimal Equilibrium Learning Over Dynamic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17601 - Efficient Edge-aware Attention Network for Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28618 - From Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28090 - MLIPS: Multi-Layer Indexer Pool Sharing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27438 - Shaped SAEs: Expanding the Toolkit for Mechanistic Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27375 - Dissecting the Impact of Model Misspecification in Data-driven Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.00626 - TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27256 - LiBRA: Logit Fingerprints for Byzantine-Robust Client Selection in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27357 - On the Fragility of Tasks under Composition: Implicit Budgeting in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27190 - Near-Optimal Regret Bounds for UCB-Style Gaussian Process Bandits via Data Thinning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28136 - Constant Step Sizes for Muon-Type Spectral Optimizers on Strongly Convex Quadratics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27747 - Don't Skip the Baseline: A Controlled Comparison of Dynamic Expert Skipping in MoEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28369 - Do Neural Models Prefer Their Submodels? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28439 - WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28590 - On-Policy Transition Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28048 - Weight Space Learning for Certifiable Few-shot Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.06970 - Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10460 - Detection of Memorization in Diffusion Models Through Thermodynamic Singularity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27754 - TTCS: Test-Time Curriculum Synthesis for Self-Evolving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22628 - Multi-Marginal Inverse Optimal Transport for Contrastive Learning Via Explicit Anchor-Positive-Negative Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33741 - Variance Reduction with Delayed Feedback for Non-Convex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28510 - Geometry-Agnostic Data-Driven Discovery of Extreme Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28487 - Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.01553 - Curriculum-Augmented GFlowNets For mRNA Sequence Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03811 - Can Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27555 - Ontic state recovery through prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27139 - What Not to Erase: Saliency-Constrained Augmentation for Low-Resource Handwritten Character Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27309 - Bug or Feature$^2$: Weight Drift and Activation Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17659 - QML-PipeGuard: Detecting Channel-Substitution Attacks on Quantum Machine Learning Pipelines in Untrusted Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25066 - Exploration via Activation-Space Steering for Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27012 - DStill: Trajectory Consistency Distillation for Accelerated One-Step Drafting in Block Diffusion Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27379 - JAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28203 - Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03929 - A Radiation-Hardened, Fault-Aware Quantized Neural Network That Self-Heals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27621 - Coincidence-Maximizing Customer Clustering Using Smart Meter Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28178 - Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08062 - GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21035 - SCOPE: Scalable Training-Free Semantic Coreset Selection for Long-Tailed Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12976 - MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27491 - Curriculum Learning for Generative Flexible Docking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28145 - ECG for laboratory values:A comprehensive physiological and technical analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28507 - Tabular Foundation Models Can Learn Association Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14622 - Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27954 - Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26914 - How Much Do $\ell_1$ Attacks Need Concentrated Perturbations? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27773 - ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28212 - Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28543 - From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28027 - Ammonia-Hydrogen Phase Equilibria in Planetary Envelopes from First-Principles-Based Machine-Learning Molecular Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27136 - SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03022 - EMBER: Predicting TCR--pMHC Binding Without a Docked Complex Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27334 - Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27150 - Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27891 - VampPrior Unleashed Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27322 - Adaptive Multi-Token Prediction: How far should we go? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28619 - SAPD: Learning from Agent Experience without Environment Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27847 - Bayesian Neural Networks via Dirichlet Process Priors on the Data-Generating Distribution for Randomized Value Functions in Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27570 - Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28409 - Beyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM Arenas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27447 - Reconstruction-Optimized Expert Pruning for Mixture-of-Experts Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27123 - Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27304 - Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.23053 - Bellman Optimality of Average-Reward Robust Markov Decision Processes with a Constant Gain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14203 - Jacobian Descent for Multi-Objective Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.16232 - Solving the Ho--Nguyen Conjecture for Gaussian Mixtures: Applications to Mixtures of Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27265 - Marginal Calibration Masks Generator Differences in Held-Out Evaluation of Multivariate Time Series, with an Application to ERA5 Weather Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33761 - HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21436 - Ensemble-Aware Structural Encoding (EASE): Conditioning Protein Encoders on Peptide Conformational Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27638 - Learning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27614 - OptScientist: Automated Discovery of Optimization Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28562 - RANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28010 - EEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27738 - Two Is Enough: Binary Classification Priors Suffice for Multi-Class In-Context Tabular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27569 - Deep catastrophic-risk-aware reinforcement learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27214 - Ranking Bandits for Carousel Interfaces with Observable Browsing Depth Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.05220 - Gibson Env: Real-World Perception for Embodied Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1808.10654 - TEX: Test-Time Scaling Testing Agents via Execution-based Cross-Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27290 - CNN-based classifier for subject-independent MBTI Extraversion/Introversion preference classification from short-time EEG signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28442 - ORBIT: Autoregressive Time Series Generation via Next Frequency-Band Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27000 - Binarization Flattens the Score Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35797 - Follow the Mean: Reference-Guided Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10302 - Blackbox Performance Analysis of LLM-based Network Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24348 - Building Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27993 - Geometry-Dependent Online and Offline Approximation for Non-Monotone DR-Submodular Maximization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00545 - KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09365 - Dynamic System Inspired Continuous Large Language Model for AI4Science Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26959 - Activation Sensitivity as a Unifying Principle for Post-Training Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11663 - Robust Residual Correction via Selective Deployment for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22428 - Generalized Convexity and Smoothness via Conjugate Duality, with Applications to Deep Network Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09523 - Debiased Prior-Data Fitted Networks for Amortized Bayesian Semi-Parametric Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28314 - Neural Implicit Energy Optimization for LiDAR Mapping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28598 - Engram Memory Network: Brain-Inspired Prototype Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27770 - Near-Duplicate Image Selection Transfers Preferences in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27943 - Glass-Box Deep Reinforcement Learning for High-Speed Flow Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27132 - LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections (Full Version) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13265 - Entropic perspective on AI resilience, data-minimal learning and optimal control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.14421 - Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28388 - AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27558 - Dynamic Model Merging Made Slim Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18904 - Interdomain Attention: Beyond Token-Level Key-Value Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24330 - Annealed correlation and quenched noise sensitivity in biased deep neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27983 - Recommending Bacterial Cultivation Conditions from 16S rRNA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28310 - $H^2(\Omega)$ A Priori Error Bounds for Boundary-Adapted PINNs Solving Elliptic Dirichlet Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19167 - Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27047 - Anytime-Valid Runtime Monitoring of Learned Barrier Certificates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27726 - Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15633 - From POMDP Theory to Deep RL with Particle Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27575 - High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26866 - Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28498 - OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13886 - A Bochner Weitzenb\"ock Decomposition for Cellular Sheaf Laplacians, Curvature and Neural Sheaf Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28455 - Agents-as-Peers: Bias-Controlled LLM Evaluation as Multi-Agent Peer Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02589 - LaLa-World: Scaling Latent World Models with Natural Language Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27851 - An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08270 - Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.23463 - Low Residuals, Wrong Value: Learning the Viscosity Solution of Hamilton-Jacobi-Isaacs Equations with PINNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27193 - How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23946 - Physics Inspired Neural Networks Enable Efficient Graph Coloring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.01503 - On Johnson-Lindenstrauss Transforms for Byzantine-Robust Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27989 - Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26974 - Manifold-Informed Neural Networks for Low-Label ECG Electrolyte Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28322 - Attractive Faces Skew Text-to-Image Reward Models and Leaderboards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28195 - GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28512 - CoASFL: Coupled Consistency Optimization for Asynchronous Split Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26992 - Foreword: Pre-Generation Prediction and Characterisation of LLM Test Failures using the Jacobian Lens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28187 - A Theoretical Analysis of Environment-Aware Out-of-Distribution Detection for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27211 - EGiME: Entropy-Guided Model Evaluation in Few-Shot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27029 - Evolving Semantic Indexes for Generative Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28568 - Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10765 - SZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26972 - HierDTA: Hierarchical Structure-Aware Representation Learning for Drug--Target Affinity Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27001 - Conversational AI for Perceived Cognitive Decline Screening in Older Adults Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27344 - Robustness Analysis of Pareto-based Joint Evaluation of Fairness and Relevance in Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27850 - From Crawled to Published: A Publisher-Controlled Web Architecture for an AI-Native Internet Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2511.18354 - ECHO: Efficient Cascade with Homogeneous Operators for Distillation-Guided 100K-Sequence Modeling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28569 - Joint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27114 - DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28340 - Multimodal Reranking Is a System One Decision Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28435 - GARRET: Generative Feedback for Region Retrieval in Visual Documents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27829 - UIBK-Embedding: Effective Text Retrieval by Unifying Dense and Late-Interaction Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27195 - MOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.26902 - The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.26951 - SweepANN: A GPU-Accelerated Large-K Approximate Vector Search for Drug Discovery Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27306 - GRaSP: Latency-Aware Optimization for Geo-Distributed Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.26938 - SPAR: Stepwise Personalized Autoregressive Recommendation with Prefix-Balanced Semantic IDs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27898 - WeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.16979 - Deep learning enables urban change profiling through alignment of historical maps Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.02154 - FLINT: Fixed-budget Late Interaction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.27273 - AutoSim: A Self-Improving User Simulator for Conversational Search Evaluation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.28054 - Birthday Estimators Are Uniformly Optimal for Renyi Entropy Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.28581 - Cascade: GPU-Accelerated Out-of-Core Suffix Array Construction for LLM Corpora Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.15254 - Psy-Chronicle: Synthesizing Campus Counseling Grounded in a Student's Semester Timeline Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22140 - The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28407 - Teaching AI Agent to Play Poker Strategically Through Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27028 - TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26993 - Do LLMs Really Lack Difference Awareness? Uncovering Heuristic Substitution in Group-Differentiating Fairness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26961 - When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24993 - SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26659 - What a One-Hour Interview Does Not Tell an LLM About You: Interviews Elicit Traits, Not Decision Policies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29458 - Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27465 - Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04693 - 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 - A Two-Way Street: Surveying the Interplay between Code-Mixing and Native Languages in Text and Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27631 - ACE-Compression: An Ability-Centric Evaluation of Compressed Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27913 - EviDial: When Correct Depression Predictions Lack Evidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27541 - Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue Recovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27109 - Label Unification for Cross-Dataset Generalization in Cybersecurity NER Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.13870 - SHAM-Bench: A Span-level Hallucination Benchmark Across Multiple Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27370 - WaveCommitments: Private and Verifiable Speech-Agent Marketplaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26867 - Beyond Calibration: Temporal LLM Confidence Assessment Across Languages and Local Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27702 - AtomSD: Procedural Atom-Guided Self-Distillation for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26926 - CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27901 - CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28381 - From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and Execution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28311 - ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27611 - PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27628 - Detecting Errors in Large Language Model Responses: The Incremental Predictive Value of Hidden States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27455 - Looking Into The Past: The Impact of Context on Detecting Deceptive Statements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27407 - Exploring Recurrent-Depth Language Models for Multitask Clinical Text Processing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27559 - Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23175 - ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19388 - Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04699 - Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28173 - AnomalyJev: Towards Evaluating Image Anomaly Explanations via Claim-Level Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27565 - Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28454 - Do We Need the Largest LLMs for Every Clinical Decision? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26937 - Asymmetric Looped Transformers: Fixed Global Representations for an Iterative Decoder Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28489 - Are Linguistic and Arithmetic Circuits Dissociated in LLMs? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27790 - Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26986 - Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27648 - Stable Signer V3: 4D Deformable Primitive Splatting Is All You Need for Sign Language Production Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24926 - Every Model Leaves a Trace: Multi-Resolution LLM Fingerprinting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28434 - Disentangling Depression from Cognitive Decline in Elderly Speech Using Concurrent Clinical Assessments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26890 - Beyond the Evidence Boundary: Behavioral Mirage Under Progressive Degradation in Medical VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28000 - From Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed Repairs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26650 - FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18679 - Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept Neurons Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28189 - Randomized YaRN Improves Length Generalization for Long-Context Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23687 - KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.19024 - Same Judgment, Different Yes: Measuring Multilingual Judgment Profiles in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28066 - Explore More, Validate Less: Efficient Reflective Prompt Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27367 - Using Embedding Models to Improve Probabilistic Race Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22555 - WAFFLE: Finetuning Multi-Modal Models for Automated Front-End Development Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.18362 - No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21679 - Self-Decomposing Diffusion for Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27600 - Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27928 - More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27406 - When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28393 - Computational Typology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.15642 - SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22959 - CEFR-oriented Russian Text Simplification Using Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27237 - MedHal: a Synthetic Dataset for Medical Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.08596 - Large Flow Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28559 - Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35814 - SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific Diagrams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27841 - Target-Aware Curation of Hallucination Stress Tests for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27247 - Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27904 - How Language Models Learn Taste: Brand Preference in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28272 - Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16400 - MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27233 - The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15394 - Cache Engineering for Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28577 - How to get the best and fairest performance out of your ASR system using activation steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26994 - Harness Self-Evolution for Long-Horizon Terminal Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27435 - Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27584 - Benchmarking Arabic Dialects for Math Problems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28607 - MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28397 - Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27227 - Decomposed Relation Extraction from Aviation Accident Narratives: Evaluating Transformer-Based Safety Knowledge Discovery under Relational Sparsity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27013 - Benefit and Cost of Random-Token Replacement under Repeated Data: A Known-Entropy Decomposition and Evidence from Ten Real Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27590 - When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01074 - Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27103 - CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00889 - Muse Glimmer 30B: An On-Device Agentic Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24628 - Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27213 - NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28616 - Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28337 - From DQI to C-DQI: Automatic Codebook Generation and Evaluation for Measuring Computational Discourse Quality Index Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27937 - VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26342 - When Synthetic Speech Is All You Have: Better Call GRPO Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08409 - Scaling Agentic Data for Long-Horizon Terminal Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13166 - When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27285 - When Models Edit Too Much: On the Fidelity of Minimal Code Edits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04061 - SINT-Flow: Schema Integration using Large Language Model Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24492 - Can Language Models Replace Programmers for Coding? REPOCOD Says 'Not Yet' Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.21647 - Diagnostic Analysis for Large Language Model Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27245 - Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27908 - Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04180 - Evaluating Context Compaction on the Questions That Come Later Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27301 - OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long-Term Personal Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28491 - LoWAgent: A Low-Resource Multilingual Benchmark for Web Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27205 - Serial Depth of Adaptive Parallel Sampling: Lower Bounds and Schedules for Masked Diffusion Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25505 - CovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27677 - LAMB: Latent Multi-Hypothesis Beliefs for Long-Horizon Large Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26955 - MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious Traditions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28452 - Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under Ambiguity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28105 - Occupational Uniqueness and Wage Growth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28133 - Can Language Models Get "Aphasia" From Neuronal Ablation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28214 - Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28380 - Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28586 - RealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27295 - Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28067 - SITO: Sifting a Commercial Text-Safety API for Missed Harm and False Flags in English, Ukrainian and Surzhyk Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27178 - AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27567 - SciFigBench: A Benchmark for Scientific Method Figure Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27087 - Predicting Linear Relational Decodability Without the Relation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27241 - Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30251 - WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27597 - An Empirical Study of Development-Tuned Representation Sensitivity for Medical QA Data Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09684 - Attention-Aligned Reasoning for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03223 - Corpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27652 - MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23234 - Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08814 - The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27202 - Hearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27745 - SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19992 - BAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28092 - TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28640 - PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16372 - A Multi-granularity Interaction Network for Relational Triple Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26952 - Testing Associative Creativity in Humans and Multimodal LLMs with Difficult-to-Name Visual Stimuli Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27894 - Adaptive Stopping of Streamed Reasoning for Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27981 - PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26891 - DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15879 - TeCoP: Accelerating Diffusion Large Language Model Decoding via Tentative Context Pipelining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27583 - On the LLM Verification for Argument Graph Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27361 - Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26888 - Evaluating Tibetan Speech Recognition Across Dialects and Adaptation Regimes: A Multi-Granularity Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27002 - Tracing Recurrent and Emergent Hallucination Patterns in Decomposed Text-to-SQL Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27720 - Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27309 - PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27678 - Sharp Degree Bounds for Putinar Certificates in Terms of the Positivity Margin via Analytic Sums of Squares Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26976 - AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26865 - Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14978 - Typhoon: Gradient-Based Task-Specific Masking for Masked Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2303.15619 - Why Static Probes Fail: Context Determines Deception Feature Composition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27577 - SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29974 - DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23839 - UvA-MT's Participation in the WMT26 General Translation Shared Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27852 - GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28457 - Preference-Aware Pareto Steering for Multi-Task Speech LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27200 - Multimodal Ambivalence and Hesitancy Recognition with Bidirectional Audio--Text Cross-Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26868 - Reward Misspecification Degrades Chain-of-Thought Monitorability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28303 - GRID: Modeling Health Influencer Discourse as Argument Networks for Credibility Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27149 - Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24809 - Memory as Code: Declarative Retrieval over Codified Long-Term Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27700 - Judging the Justification: Decision Certificate Supervision for Generative Reward Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27528 - Cross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic Screening Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27043 - Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17544 - Ask to Distill: Learning to Synthesize Data for On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27450 - Fluent but Fallible: Benchmarking Hallucination and Factual Reliability in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27034 - Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19952 - StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17309 - Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28176 - Forty Questions: Identifying a Language Model from One-Word Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28281 - African Languages AI Safety Readiness Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27269 - Using Letter Positional Probabilities to Assess French Word Complexity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28040 - LongHisDoc: A Comprehensive Benchmark for Chinese Long Historical Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14531 - ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Object Placement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16011 - Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25964 - SMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual Rubrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27820 - A Survey of Generative Categories and Techniques in Multimodal Generative Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10016 - Matrix Multiplication from Polynomial Packings: A Constructive and Elementary Proof of $\omega\le9/4$ Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.28627 - Short Point Lists for CNFs and Stronger Constant-Depth Circuit Hardness Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.27127 - Theorem prover Arend Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27264 - Automatic Differentiation with Constraints in Forward and Inverse Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27888 - Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27548 - MADDIE: Multi-Agent Drug Discovery Engine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16975 - S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27746 - VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25043 - Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04943 - RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28351 - Evolving Self-tuning Benchmarks for Long-Horizon Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27307 ## Community - Today's PHP Security Release, and How We're Strengthening PHP Security Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/21/php-security-release/ - Fragments: October 21 Source: martin-fowler Topic: Architecture (+AI, JavaScript, React) URL: https://martinfowler.com/fragments/2026-10-21.html - Panache — RTS Belle Époque pour mobile Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/21/panache/ - Jaime Buelta: Jev webinar video Source: planet-python Topic: Python (+AI) URL: https://wrongsideofmemphis.com/2026/10/21/jev-webinar-video/ - Show HN: Omnara – Open-source alternative to Claude Managed Agents Source: hacker-news Topic: General (+AI, PostgreSQL) URL: https://github.com/omnara-ai/omnara - Embedding EYG in Erlang programs Source: lobsters Topic: General (+AI) URL: https://eyg.run/guides/embedding-eyg-in-erlang-programs - Patch the Planet: global response coordination as agents uncover vulnerabilities Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/coordinated-disclosure-of-critical-vulnerabilities/ - Using thousands of AI agents to uncover new leads in biological data Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/scaling-ai-research-for-complex-biological-data/ - OpenAI models are coming to Google Cloud Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/openai-models-google-cloud/ - Using LLM for confidence scoring is a bad idea Source: hacker-news Topic: General (+AI) URL: https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html - Using Claude to reduce the attack surface of code Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/research/attack-surface-reduction ## Media - Which model should I use? | The Agent Factory Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=7ZqwcaRX-c0 - Why your overnight AI agent paused after 10 seconds Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/9qXaDUAGsrY - LIVE STREAM: Training Agents IRL Seminar Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=f9VsJsAIV7E - I Turned Structured Output Into a Game 🎮 Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/shorts/KnDMnZYEo2M - Automate Merge Request Reviews with GitLab Duo Agentic Code Review Source: youtube-gitlab Topic: Open Source (+AI) URL: https://www.youtube.com/watch?v=YG6A3w7_x5U