TILens Daily Edition 2026-10-07 Filters: topic=ai, github=hidden Stats: 750 articles, 28 sources, 694 research papers Top topics: AI, AI Research, Information Retrieval ## News - Multimodal open d1 decision models for the edge Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/LiquidAI/open-d1 - Claude Haiku 5.5 is now available on AWS Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/claude-haiku-5-5-aws/ - Claude Haiku 5.5 is now available on AWS GovCloud (US) Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/claude-haiku-5-5-aws-govcloud/ - Introducing Falcon ASR Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/tiiuae/falcon-asr - One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/nvidia/nemotron-ioi-and-imo-2026 - Helping teens learn, plan, and shape the future of AI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/teens-learn-and-plan - Radisson Hotel Group brings hotel discovery into ChatGPT Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/radisson - GPT-6 and Intelligent UI for everyone Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/gpt-6-for-everyone - Claude’s cyber safeguards are getting more flexible — but not for everyone. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/anthropic-cyber-access-tiers/ - Decision models are suddenly everywhere. OpenAI’s is now public. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-decision-models-deployment/ - Anthropic Gives Vetted Defenders Fewer Claude Guardrails Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/vulnerabilities-threats/anthropic-vetted-defenders-claude-guardrails - OpenAI dots inspire open source imitators amid technical difficulties Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/07/openai-dots-inspire-open-source-imitators-amid-technical-difficulties/5301734 - OpenAI Agent Escape Causes Wikimedia Service Outage Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyberattacks-data-breaches/openai-agent-escape-causes-wikimedia-service-outage - What Are Agents and How Do They Work? Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/what-are-agents-and-how-do-they-work - Microsoft Wants Your PC to Work While You Sleep, Surface Laptop Ultra Pre-Orders Open Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/microsoft-windows-hybrid-ai-agents-rtx-spark/ - OpenAI’s former safety lead says it’s shipping “new capability and risk every Tuesday” Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-safety-release-cycle/ - Step Caps, Timeouts and Retries for LLM Tool Loops in Node.js Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/geminate_solutions_9b6035/step-caps-timeouts-and-retries-for-llm-tool-loops-in-nodejs-42c2 - ChatGPT is getting a lot more visual, with the launch of a new interface Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/07/chatgpt-is-getting-a-lot-more-visual-with-the-launch-of-a-new-interface/ - Anthropic launches Haiku 5.5 at a much lower price Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/anthropic-claude-haiku-5-5/ - I asked an LLM which listings to skip. It kept getting the numbers wrong. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/gk_019a1c50f0a200e67225e0/i-asked-an-llm-which-listings-to-skip-it-kept-getting-the-numbers-wrong-4p41 - Poetry is the new AI security threat as PoeLLM malware infects 3K+ servers Source: theregister Topic: General (+AI) URL: https://www.theregister.com/security/2026/10/07/poetry-is-the-new-ai-security-threat-as-poellm-malware-infects-3k-servers/5301672 - How Netflix Taught an LLM to Recommend Movies So That You Keep Watching Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/how-uber-built-a-genie-to-answer - OpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/07/openais-alexander-embiricos-is-coming-to-techcrunch-disrupt-2026-days-after-the-launch-of-dots/ - GPT-6.1 Sol vs. GPT-6 Astra: Same accuracy at 18% of the cost Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/gpt-6-1-sol-vs-gpt-6-astra/ - Get hands-on: The full lineup of interactive roundtables at TechCrunch Disrupt 2026 Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/07/get-hands-on-the-full-lineup-of-interactive-roundtables-at-techcrunch-disrupt-2026/ - Google rolls out improved SynthID AI content detector, now available globally Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/ai/2026/10/google-rolls-out-improved-synthid-ai-content-detector-now-available-globally/ - AI/ML is becoming a performance factor in motorsport Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/cars/2026/10/ai-ml-setups-became-a-tool-in-indycar-champion-alex-palous-toolbox/ - Validate LLM Output: Catching AI-Invented Emoji Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/rain_880203/validate-llm-output-catching-ai-invented-emoji-4bf9 - Security updates for Wednesday Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1099202/ - Mega Carrots for Monty, Angular Through the Sliding Door, and Lynx on Foldables Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/thereactnativerewind/mega-carrots-for-monty-angular-through-the-sliding-door-and-lynx-on-foldables-ck7 - The Tiny Ultrasound Chip Behind Butterfly’s Bigger AI Bet Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/butterfly-ultrasound-chip-medical-ai/ - Mistral’s New AI Model Puts a Price on Sovereignty Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/mistrals-new-ai-model-puts-a-price-on-sovereignty/ - Q4 TNA Email - Send 2 of 3 Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/q4-tna-email-send-2-of-3/ - Q4 TNA Email - Send 3 of 3 Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/q4-tna-email-send-3-of-3/ - OpenAI's math avalanche continues Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/openai-math-avalanche-continues - 😺 OpenAI’s AI produced 722 math manuscripts Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-s-ai-produced-722-math-manuscripts/ - Altern #26 - New Models, Better Tools, More Ways to Build Source: altern-newsletter Topic: AI (+AI Tools) URL: https://newsletter.altern.ai/p/altern-26-new-models-better-tools - Dario Amodei’s $18 Million Pay Opens a Bigger Question About AI Wealth Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/dario-amodei-compensation-anthropic-ipo-ai-wealth/ - "LLM streaming works in the demo. These 4 hops break it in prod" Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/ajayvish01/llm-streaming-works-in-the-demo-these-4-hops-break-it-in-prod-50pp - Apple's home ecosystem 🏠, OpenAI math 🧮, state of tech 👨‍💻 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-10-07 ## Research - Does better work always mean better workers? Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/does-better-work-always-mean-better-workers/ - How Wrong Is Your Marketing Mix Model (MMM)? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-wrong-is-your-marketing-mix-model-mmm/ - Introduction to Reinforcement Learning: Multi-Armed Bandit Simulation in Python Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/introduction-to-reinforcement-learning-multi-armed-bandit-simulation-in-python/ - The Consistency Quadrant: A Visual Guide to LLM Reliability Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/the-consistency-quadrant-a-visual-guide-to-llm-reliability/ - When Do PINNs Beat Classical Numerical Methods? A 1D vs 5D Experiment Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/when-do-pinns-beat-classical-numerical-methods-a-1d-vs-5d-experiment/ - ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23314 - The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22278 - Learning from Hindsight for VLA Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09042 - Near-Optimal Sample Complexity for Recursive Entropic Risk Reinforcement Learning with a Generative Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06931 - Adaptive Latent Capacity for World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32921 - Contact Geometry and Covariance Deficits in Volume-Sampled Least Squares Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26877 - Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08129 - FFR: Forward-Forward Learning for Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03927 - Prediction-powered inference for time series across space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08715 - DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.24574 - SquidAgent: Parallelize Wisely, Coordinate Efficiently Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08647 - Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00729 - Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.18158 - Direct Regret Optimization in Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.06529 - Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07417 - Information-Dense Synthesis for Molecular Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08495 - SoloQ: Calibration-Free Quantization for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07121 - Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04142 - Two-Sample Testing for Random Graphs without Vertex Correspondence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07503 - APEX: Speculate smarter, not deeper Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07780 - Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07399 - Learning to Remember: Distilling Memory Retention for Compact Recurrent Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06942 - Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07816 - DePICT: Decision-Preserving Interface for Constrained Downstream Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03945 - Targeted search shows that random-device testing underestimates worst-case error in a simulated wave-based neural operator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07529 - Random Feature Gaussian Process Attention: Linear-Time Probabilistic Attention with Calibrated Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08578 - Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08090 - A Sharp Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06866 - How Much Can Language Models Gain from Test-Time Computation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01110 - Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08670 - Systemization of Knowledge (SoK): Human-Centered AI Safety for Youth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08554 - Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08077 - Local Sparsity Enables Unsupervised LLM Safety Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20129 - Cross-Modality Controlled Molecule Generation with Diffusion Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.14748 - Steering Diffusion Models to Rare Events with Sequential Monte Carlo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08652 - Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11570 - Variance-Optimal Off-Policy Evaluation with Conjunct Effect Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08677 - Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07704 - When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08718 - Surviving the Router: Optimizing Skill Injections for Retrieval and Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08098 - QF3: Fast Flow RL with Filtered Q-Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08789 - Flow-Transformed Implicit Processes for Function-Space Variational Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01954 - Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07737 - Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07899 - The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08314 - How Many Independent Samples Does a Satellite Image Contain? Generalization Bounds for Spatially Dependent Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08227 - Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07782 - Does On-Policy Distillation for Safety Pose Backdoor Risks? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07654 - PyDPF: A Python Package for Differentiable Particle Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25693 - Beyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08173 - PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16419 - AEGIS: Runtime-Guided GPU Collocation for Multi-Tenant Deep Learning Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19073 - FreDF: Learning to Forecast in the Frequency Domain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.02399 - HARL-A: An Extensible Benchmark Framework for Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLab Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01264 - Neural Algorithmic Reasoning for Graph Saddle Point Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07255 - Online Neural Space Time Memory for Dynamic Novel View Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15271 - Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07005 - KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14777 - Express Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10944 - Voice "Cloning" is Style Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16578 - Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07910 - Learning PDE solution operators with variable initial conditions via Latent Dynamics Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08475 - Lossy Compression of PDE Training Inputs: Field Reconstruction Error Does Not Order the Cost to a Trained Operator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06095 - Singular Value Decomposition: A Geometric Rediscovery, Where Proofs Become Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08565 - Data, Numbers, and Geometry: Three Tutorials on Numerical Methods, Machine Learning, and Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07220 - Anytime-valid simulation-based hypothesis testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08210 - Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07894 - On the Computational Tractability of Robust Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08740 - RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11958 - EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05446 - Comparative review of hybrid forecasting models for short-term prediction of building thermal load Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06881 - Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07489 - Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06883 - Extending Pathwise Gradients to Discrete Random Variables via Finite-Order Relaxation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07786 - Exact Calibration and Sharp Risk Geometry for Volume-Sampled Ridge Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07721 - Trustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07755 - Attenuated in-context identification in time-series foundation models: diagnosis under counterfactual inputs and repair by synthetic forced-system fine-tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08118 - ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07323 - JIVEAdapter: A Multi-Task Additive Low-Rank Adapter via Joint and Individual Variation Explained (JIVE) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07036 - Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07553 - Lock-in EP: An In-Situ Training Algorithm for Oscillatory Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07283 - We Need Explanation Cards to Connect Explanation Algorithms to the Real World Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16786 - FlexiFlow: Bandit-based Model Switching in ML Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07286 - Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08540 - The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07723 - Federated Mixture-of-Experts Alignment on Mobile Edge Networks under Data Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21276 - Optimal and Efficient Online Inverse Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08735 - Joint Workflow and Prompt Optimization for User Behavior Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07663 - A Neural JKO Scheme for Hellinger-Kantorovich Gradient Flows via Monge-Growth Pairs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07602 - AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07457 - Mapping the Emergence of Regularization-Driven Dynamics in Grokking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25813 - Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07906 - Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07475 - Online Conformal Prediction for Non-Exchangeable Panel Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17705 - Reinforcement Learning over Predictive Distributions for LLM Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20740 - Algorithmically Aligned Neural Agglomerative Tree Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07271 - Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07565 - StaFIR: Convex Learning of Stationarity-Aware Causal Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07430 - CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07177 - Improving Mixup Calibration with Wasserstein Distributionally Robust Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.17874 - Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08055 - A perspective note on likelihood approximation and inference for complex simulation models using a chain of aggregated normalizing flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07391 - Recurrent Looped Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07591 - WASD: Wasserstein-based Knowledge Distillation for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07706 - AccentCL: Robust Accent Classification with Incremental Expansion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07426 - FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18964 - Time-o1: Time-Series Forecasting Needs Transformed Label Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17847 - Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07781 - Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07491 - Interpretable Hypergraph Learning via Neural Additive Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07458 - MetaLearnNCA: Few-Shot Offline Meta-Learning via Interacting Neural Cellular Automata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08479 - Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08164 - Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07739 - Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20718 - Learning Disentangled Representations with Quantum Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07196 - On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04332 - FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29695 - Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07859 - REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07585 - Climbing the Design Ladder: Sequential Knowledge Distillation for Early-Stage Circuit Timing Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08457 - Weight Oracles: Reading Neural Network Weights with Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07334 - Conditional Flow Matching for Transport Between Markov Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07229 - Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07981 - Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06880 - On the Intrinsic Limited Robustness of Latent-Based Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08178 - ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34457 - Scen-Opt: A Scenario Optimization Toolbox for Data-Driven Convex Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07846 - Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07607 - What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07269 - Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17050 - Global Transport Couplings for Classifier-Free Guided Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07555 - Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07444 - A Systematic Study of Small Language Models on Abstract Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08680 - Efficient Multimodal Inference through Adaptive Acquisition and Sequential Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07466 - RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07720 - Grand Canonical Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00683 - AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08773 - Optimization Encoders: Rethinking Second-Order Meta-Learning for Neural Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08075 - Learning a Ranking from Human Feedback in Log-Concave Random Utility Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07973 - Learning to Retrieve via Reinforcement Learning in Embedding Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07731 - What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07405 - Nonlocal Hamiltonian Dynamics on Sparse L\'evy Graphs: Spectral Analysis and Multimodal Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06904 - DeepAJM: Deep Association Joint Model for Irregularly Sampled data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07388 - HyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07383 - GeneICL: A Tabular Foundation Model for Bulk Transcriptomics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08694 - Identity-Conditioned Score Fusion for Open-Set Person Re-Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07366 - PRUE: A Practical Recipe for Field Boundary Segmentation at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27101 - Boosting Large Language Models with Mask Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22764 - Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07699 - Probabilistic Counterfactual Inference for Discrete Outcomes in Gaussian-Process Causal Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08689 - Preserving Unstable Modes Through Inverse Dynamics in JEPA World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07540 - sHAIL-Causal: A Sequential Staircase Procedure for Invariant Causal Predictor Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07057 - Generalized Matheron Variational Implicit Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07938 - Structuring MoE Expert Selection for Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07332 - ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15983 - Reinforcement Learning with Segment Reward Feedback under Linear Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08271 - Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07808 - Mechanistic Interpretability of Atmospheric Rivers in GraphCast Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07583 - Particle Monte Carlo Tree Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08982 - Adversarial Training for Deep Hedging in Nonstationary Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07162 - Explaining Attention with Program Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19317 - Stochastic Penalty-Barrier Method for Constrained Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18618 - SketchSSM: Write to the Full State, Read from a Compact Sketch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33051 - From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05660 - Seeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07558 - Hub for Outliers, Spokes for Inliers: Uniform Latent Space Construction for Dual-Mismatched Semi-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07610 - Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07447 - PHBA: Prefix-State Hybrid Block Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08527 - Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08337 - Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08159 - Learning Explainable Representations of Complex Game-playing Strategies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07638 - Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23044 - Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07677 - X-OPM: Explainable Automatic Digital On-Chip Power Modeling for Enhanced Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08502 - Towards the Automatic Synthesis of Interpretable Chess Tactics Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.07640 - The Geometry of Statistical Feature Learning in Mean-Field Langevin Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31429 - Time-multiplexed layer reuse for physical neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.00044 - The Terminal Representation in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31289 - Asymptotic Analysis of Empirical Risk Minimization on Entry-wise i.i.d. Heavy-Tailed Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07637 - ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14285 - Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06890 - Sample-Optimal Estimation of the Fr\'echet Inception Distance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07114 - Investigating Model Compression for Neural Machine Translation in the Biomedical Domain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07032 - [b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18899 - CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07576 - AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06949 - Reward-Driven Learning under Prompt-Level Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07212 - Should We Skip Diffusion? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07002 - Predicting kernel regression learning curves from only raw data statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.14878 - Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07485 - Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07258 - CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07132 - Variational Physics-Informed Ansatz for Reconstructing Hidden Interaction Networks from Steady States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13708 - A self-learning scientific agent for X-ray diffraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07862 - LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08176 - TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07559 - Component and Dimension Sparsity in Transformer Refusal Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06903 - Towards One-for-All Foundation Model for Attributed Graph Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07778 - Early Memory Selection for Balanced Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08624 - FedDermaSeg: Federated Learning for Dermatological Image Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08574 - Hierarchy-GBP: Accelerating Factor Graph Inference via Abstraction and Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06978 - Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07966 - SSR: Sparse Segment Reduction for Ternary GEMM Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08403 - Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07406 - XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05866 - Learning Decision-Stump Thresholds in Context: Dynamics of Softmax Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07074 - Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07572 - A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07290 - Learning Visual Feature-Based World Models via Residual Latent Action Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07079 - Muon Is Theoretically Wrong For Convolutions, But Empirically Effective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07103 - Stability of Measure-to-Measure Transformers on Sub-Gaussian Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07717 - A Riemannian Geometry for Low-rank Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08049 - Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08743 - Assumption-lean logistic regression with missing covariates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07292 - Symmetry-Aware Feature Learning: A Polynomial Separation for Multi-Index Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08420 - Learning Scientific Exploration from Human Research Decision Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07184 - Less Is More: A Leakage-Controlled Study of Dermoscopic Preprocessing for Joint Skin Lesion Classification and Segmentation with YOLO26 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08570 - Does Scaling Reinforcement Learning Really Require More Training? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01133 - On-Policy Distillation with Negative-Policy Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07874 - Source-Learned Reliance for Selective Test-Time Adaptation of Multimodal Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07499 - Convergence of Sharpness-Aware Minimization Algorithms using Increasing Batch Size and Decaying Learning Rate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.09984 - Label-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation Tools Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07885 - Uncertainty Localization in LLM Reasoning via Embedding Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02427 - FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08537 - Causal Effect Estimation under Networked Interference without Networked Unconfoundedness Assumption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.19741 - STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07006 - Neural Global Optimization via Iterative Refinement from Noisy Samples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03614 - Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04946 - The Geometry of Empowerment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07796 - Learning Probabilistic Filters with Strictly Proper Scoring Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26497 - Inference-Time Projection for Physically Valid Biomolecular Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07037 - TTNet: Multi-Task Deep Learning for Table Tennis Player Analysis with Smart Racket Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07823 - Data-driven measures of high-frequency trading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.08101 - What Must Replay Preserve? Separating Correctable Bias from Class Correspondence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07077 - EVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06970 - FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08016 - Exact-Solution Volume and Length Generalization in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07676 - Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08021 - TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07043 - Secure Speculative Decoding for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08678 - Beyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08533 - Extending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06920 - Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07470 - World Properties without World Models: Distributional Associations and the Interpretation of Decoding Results from Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04317 - Foundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07550 - CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07668 - Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08123 - Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07232 - Interleaved Projected Gradient Descent for Safe Imitation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07167 - Algorithm Selection with Zero Domain Knowledge via Text Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.19753 - ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07061 - Stochastic Siamese MAE Pretraining for Longitudinal Medical Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23441 - Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07522 - AnyBottle: A Recipe to Only Keep the Concepts You Really Need Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08552 - SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03372 - Mu-DisCoCat: A Variational Pipeline for Compositional Generalization on Quantum Processors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08131 - High-Dimensional Statistical Inference for Sparse Support Vector Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08345 - Uncertainty Quantification Is Indispensable for Reliable Connectome-Based Graph Learning: A Narrative Review and Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08353 - The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07131 - AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06927 - The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26423 - A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06980 - ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.07863 - Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07834 - Fast and Efficient Asynchronous Gossip Algorithm for Robust and Non-Smooth Convex Decentralized Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.20571 - DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06993 - Consideration Circuits: Depth Separation and Universality Beyond a Single Softmax Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04143 - Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.00053 - Process-Aware AI for Rainfall-Runoff Modeling: A Mass-Conserving Neural Framework with Hydrological Process Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25093 - Minimal Witness Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07226 - Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06950 - Distributionally Robust Mixture-of-Experts Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07207 - ApexQuant: Data-Free Elastic Quantization by Residual Re-Isotropization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07904 - Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08738 - Neural Scaling Laws for Jet Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28940 - Benchmarking Label-Revealed Online Updates for EEG BCI Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07420 - RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08571 - Structure-Aware Graph Abstention for Reliable Selective Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08322 - Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07247 - Reperesentation Geometry Matters for Planning with JEPA World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16287 - Repair Lot Skyline: A Weighted Constraint Satisfaction Approach to Pavement Repair Optimization from Geospatial Hazard Density Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06989 - Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23073 - Constant-Curvature Sliced Gromov-Wasserstein for Heterogeneous Cross-Curvature Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07218 - Behavioral Cloning Mystery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07056 - Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07518 - Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08785 - Trajectools Demo: Towards No-Code Solutions for Movement Data Analytics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06858 - Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07115 - Action-Driven Processes for Continuous-Time Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.26672 - Behavioral Guarantees for Proxy-Based Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10680 - ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08078 - Jailbreaking Open-Weight LLMs via Random Embedding Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07125 - Where Do Two Populations of Persistence Diagrams Differ? Calibrated Local Inference at a Fixed Budget Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08292 - TICDA: Tabular In-Context Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07996 - Privileged Context as Drift in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07842 - Machine learning Majorana topology using unsupervised and supervised learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13825 - Generalizable Dense Reward for Long-Horizon Robotic Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00055 - A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07857 - Learnable Spectral Activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07419 - Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02659 - Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08452 - Rapid Fredholm stabilization of the Kuramoto--Sivashinsky equation with unrestricted, spatially-varying anti-diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08764 - Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30995 - Uniform Discrete Diffusion Models are Minimax Optimal for Estimating Distributions with Small Effective Support Size Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07655 - Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07712 - CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08592 - When Attention Does Not Explain the Peak: Temporal Reference vs. Forecast Output in Attention-Based Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07080 - Low-Rank and Structured Sparse Tensor Decomposition for Anomaly Detection in Multivariate Functional Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06930 - Finding the Heads and the Neurons Responsible for Network Information Retrieval in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.08200 - SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16193 - Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08560 - Sinkhorn doubly stochastic attention rank decay analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07925 - Latent space bias directions in LLMs capture confidence, not fairness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08559 - Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07853 - A Footprint-Aware, High-Resolution Approach for Carbon Flux Prediction Across Diverse Ecosystems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01917 - Probabilistic Truly Unordered Rule Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.09918 - SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07484 - MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07809 - Axiom Satisfiability of Linear Rewards in Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06892 - Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06854 - Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06889 - DeltaTTT: Layerwise Optimization for Nonlinear Recurrent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08553 - MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09364 - Explore, Then Commit: Measurement-Efficient Scientific Law Discovery with Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07620 - Uncovering Cross-Objective Interference in Multi-Objective Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06869 - A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20980 - Decision-Focused Learning in MDPs: An Occupancy Measure Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08384 - Quality-Controlled Active Learning via Gaussian Processes for Robust Structure-Property Learning in Autonomous Microscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29135 - Artifact removal improves electrodermal waveforms but not downstream classification in a virtual-reality balance task Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07438 - Can an MLP Absorb Its Own Skip Connection Exactly? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23705 - Modeling Latent Disturbances for Robust Decision-Making in World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07599 - A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07990 - Stateless Language Agents: Scaling Long-Horizon Automated Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07625 - TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07767 - Scalable extraction and visualization of multi-attribute logical and functional dependencies in tabular data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08287 - CANDLE: Cortical Null-Space Decomposition for Noninvasive Brain Source Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07824 - RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07349 - Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08722 - Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.03647 - LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07111 - Data Fusion for Errors-in-Variables Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07048 - $\alpha$Transfer: Coefficient Transfer for Efficient Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07819 - AMBER: Training Long-Horizon Web Agents through Append-Only Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07118 - Feature Information Dynamics in Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08626 - Von Neumann Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05780 - SanSi: A Looped Typed Decision Model for System 1.5 Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07730 - Inference and learning in sparse autoencoders as natural gradient flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07389 - Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06840 - Energy-Aware Path Following: Comparative Analysis of Reinforcement Learning and NMPC for Electric Vehicles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08112 - DecepEval: A Benchmark for Evaluating Deception in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07967 - On Color Alignment in VAE Latent Spaces and Its Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07072 - TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06855 - PuzzleJAX: A Benchmark for Reasoning and Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16821 - When Can World Models Recover Physical Laws? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06877 - From Shared Demand Patterns to Local Uncertainty: Probabilistic Load Forecasting by Mixing Compact Adaptations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08538 - LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08246 - Evaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07345 - A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07084 - SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07086 - Systematic Evaluation of TabPFN-TS and Chronos-2 for Zero-Shot Heat Load Forecasting in District Heating Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20024 - Task diversity produces systematic transfer but inhibits continual reinforcement learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00880 - An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06988 - Detecting a Shift Is Not Enough: Exact Minimax Limits of Linear Representation Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08069 - Intersectional Fairness via Mixed-Integer Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19595 - Do Neural PDE Solvers Learn the Right Dynamics? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06952 - Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07060 - FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07898 - Compact Robot Policies Need Fine-Grained Visual Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08183 - How Bregman Divergences Shape Shampoo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08534 - How Inefficient Is Natural Gradient Descent? From Exact Optimality to \Theta ( \sqrt{ \log d } ) Divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07228 - Memory Prediction Excess: A Probabilistic Quantity for Predictive Gain and Memory Length in Stochastic Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06894 - Uncertainty in Representation Learning on Knowledge Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06974 - Is this machine playing? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07130 - Neuromotor Hierarchy Network: Physiological Inductive Biases for Robust Generalization in sEMG Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07713 - Mask-Guided KV Cache Eviction in Block Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06996 - Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08400 - Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08561 - UNREAL: Unifying Retrieval and Long-Context with a Single Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08463 - Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07009 - Computationally efficient goodness-of-fit tests through kernelized Stein discrepancy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20007 - Exact Unlearning via Quantized Sufficient Statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07197 - Performative Prediction with Selective Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08272 - DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08268 - BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07594 - Stepped MoE: Segment-Level Routing with Configurable Inference Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07348 - Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07551 - Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06964 - SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23753 - Scale-Invariant Training for Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07324 - Learning a Mixture of GFlowNets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07562 - Variational-Ising-Attention:Tailored Attention Matters for Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23634 - Stochastic Gradient Descent Ascent is Suboptimal for Nonconvex-PL Min-Max Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07814 - Beyond Scaffold Splits: Structural-Frontier Evaluation Reveals Hidden Failures in ADMET Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10729 - Retrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17508 - Advantage of Entangled Learning Rules in Quantum Measurement Class Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07328 - Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06918 - SepsisLens: Structure-Preserving Sequence Modelling for Decomposable Early Sepsis Warning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08046 - Mean-based algorithms: A lower bound and regret Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04931 - Learning to Simulate Individuals from Macro Social Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07062 - Calibrated Answers About Randomized Trials From a 4-Billion-Parameter Open Model: A Registered Test and a License-Clean Release Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07019 - Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21075 - Identifiable World Models from Pretrained Diffusion Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07028 - Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37858 - KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34060 - Anchor Divergence for Semantic Geometry in Contrastive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06919 - An overview of machine learning-enhanced iterative methods for systems of linear and nonlinear equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07211 - Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07825 - DRtool: An Interactive Tool for Analyzing High-Dimensional Clusterings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.04603 - Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25531 - Rethinking Adapter Placement: A Dominant Adaptation Module Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06183 - MS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07662 - Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06874 - Identifiability Analysis of Linear ODE Systems with Hidden Confounders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.21917 - Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07754 - Beyond the Semicircle: Free Diffusion Models with Prescribed Equilibria Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22778 - Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17524 - PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34054 - Neural Fields Encode Adaptation Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07253 - Neural Petri flows for chemical reactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08750 - Sensor Geometry as a Flow-Matching Prior for Multi-Channel Brain Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08355 - Diffusion Model-Based Video Editing: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.07111 - OxiGen: Oxidation-State-Aware Crystal Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08296 - Explicit Asymptotic Bounds for Sequential Calibration Beyond $T^{2/3}$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07623 - Adaptive Mean Estimation by In-Context Learning: A Gradient-Flow Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07804 - Optimal Transportation and Alignment Between Gaussian Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03579 - Shaping the Wind: Nested Potentials for Kinematically Admissible Urban Wind Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07033 - LionMuon: Alternating Spectral and Sign Descent for Efficient Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35297 - Best-of-$N$ Guidance for Test-time Diffusion Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05108 - Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07243 - Valid for Free: Homophily-Gated Conformal Prediction for Training-Free Node Classification with Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08564 - ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07792 - How Learning Governs Unlearning across the Memorization-Generalization Spectrum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08577 - Deep Time-Series Forecasting in 10 Years: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19899 - A theory of platonic representations in language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07168 - Local exponential stability of mean-field Langevin descent-ascent and associated particle system Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01564 - Enhancing Diffusion Language Models with Autoregressive Post-Training Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08108 - Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08132 - Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26070 - Learning consistent molecular mechanics force fields from first principles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08020 - DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08341 - UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14049 - Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07094 - Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07613 - Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.11500 - Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07362 - Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07335 - AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07615 - To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18882 - When Explanations Compete: Policy-Aware Selection Under Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.05479 - Can LLM-assisted regularization increase forecast accuracy for migration flows in low data regimes? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07208 - Towards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07358 - Accelerating the Development of PLGA In Situ Forming Depots Through AI-Driven Multi-Objective Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08368 - CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07340 - DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08048 - Logbook: Extremely Long-form Audio Event Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07338 - Improving Proactive AI Assistance with Hierarchical Procedural Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06505 - SkillFormer: Skill-Decomposed Adaptation for Audio Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07533 - High-dimensional online calibration from harmonic weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07740 - Multigroup Fairness and Omniprediction: Separations and Equivalences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07374 - Co-Evolving Paths and Flows via Path-Flow Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08717 - Multi-Label Perceptual Bug Detection in Video Games using Deep Learning on Gameplay Footage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08593 - Rate-Optimal Algorithm for Adversarial Linear CMDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00927 - FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06947 - Does Muon Need Fine-Grained Spectral Shaping? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07497 - Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39082 - QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13966 - Learned Adaptive Multiresolution Diffusion Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07884 - Towards a Unified Misuse Monitoring Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07089 - Active Feature Acquisition for Cost-Efficient Temporal Prediction with Reduced Participant Burden Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07452 - Practical Feasibility of Gradient Inversion Attacks in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19819 - When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06861 - The Premise Is the Problem: Exchangeability Failure in Self-Monitored Test-Time Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07038 - SIFT: Search Intent-to-Filter Transformer for Multi-Task Personalized Filter Ranking at Airbnb Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07810 - Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08413 - Evolutionary One-Step Generators: Fast and Diverse Sampling for Discrete Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08367 - Can phenotypic activity be predicted without experimental readouts? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07997 - MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07511 - Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07079 - Two-Sample Testing via Generative Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08277 - What Does Fr\'echet Distance Measure? A Directional Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05518 - Enhancing Distance-Based Graph Autoencoders with Structural Penalties for Dynamic Graph Embedding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18762 - Symphony for Text Generation: Benchmarking Clinical Note Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08161 - SkillEvoLean: Mutation-enhanced skill evolution for Lean provers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01799 - E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05048 - Linear Bandits under Exact Sliding-Window Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08745 - Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22994 - QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06936 - MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08669 - CHARTER: Auditing Reference Substitution in Hierarchical Compact-Evidence Evaluation for Computational Pathology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07843 - To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06694 - VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08402 - The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07597 - CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08312 - Qubit-centric Transformer for Surface Code Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11593 - Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.18029 - PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.18169 - Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04364 - Personal-Agent Mediated Recommendation with Cross-Platform User History Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07588 - Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07628 - Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02691 - Behavior-Mining, Generative Conversations, and Collaborative Advisory: the Future of Travel and Tourism Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08232 - Smart Content Ingestion for Generative AI Workloads Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07091 - The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07309 - Enhancing High-order Interaction Awareness in LLM-based Recommender Model Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2409.19979 - Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.06902 - Hypergraph-Enhanced Dual Convolutional Network for Bundle Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2312.11018 - Diff-SQL: SQL Efficiency Optimization via Patch Generation and Constraint Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.06857 - Do We Still Need Gazetteers in the Era of LLMs? Chaining Retrieval with a Spatial Neuro-Symbolic Index Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.05028 - From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07960 - Seeing the Context: Enhancing Recommender Systems with Image-Derived Contextual Signals Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08407 - A Systematic Study of Semantic ID Spaces for Generative Information Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08732 - DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07622 - Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.34577 - Contrastive Learning for Aspect Representation towards Explainable Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07761 - RAGFlip: Measuring Query-Level Negative Flips in Retriever Upgrades Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07266 - Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08716 - Aligning Performance with Contribution: Towards Contribution-Aware Fair Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08245 - Adapting Generative Recommenders for Multi-Turn Interaction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08136 - KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.18850 - More Efficient LLM Reranking with Whole-Pool, Setwise, Long-Context Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.01782 - Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07105 - Confidence-Ordering Reversal under Contextual Priors in Neural Decoding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.08229 - WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07384 - Token-Budgeted Escalation for Financial Document QA: Cost Is Predictable, Benefit Is the Bottleneck Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07760 - SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.02387 - A Study of Prior Case Retrieval Using Lexical, Semantic, and Rhetorical Role Information in Indian Legal Documents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07437 - AX is the New AEO Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.34951 - ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07886 - Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07402 - Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.07023 - Parametrized Exact Hardware-Software Partitioning Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.08645 - TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.23065 - Visual Abstention in Unified Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07887 - More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04753 - Dream-RSI: Recursive Self-Improvement through Evolving Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14858 - Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06897 - SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05761 - AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06971 - Marking Contour Tones in Yor\`{u}b\'{a}: A Typographic and Computational Proposal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38627 - Agreement Is Not Validity: Cross-Model LLM Consensus in Diagnosing Student Failure Modes in K-12 Math Tutoring Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08703 - Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30557 - One Step at a Time: Trading LLM Autonomy for Process Predictability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07817 - Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00355 - Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27690 - Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07532 - Leveraging a four-quadrant approach for evaluating Redpine Science Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07937 - Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05647 - Who Wrote It Is Not Enough: Detecting Who Contributed the Insight Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07365 - ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07803 - POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.08082 - On Open-Ended Information Seeking for Information Elicitation Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07509 - Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07070 - SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07327 - Auditable Claims about AI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07459 - A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07339 - Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.17988 - Dynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07848 - Language-model ratings of depression reflect the rater more than the patient Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08501 - Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26823 - Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07716 - Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18225 - TeleTune: Evolving Agent Skills From Offline Telemetry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05437 - Closing Ambient Clinical Documentation Gaps with Automated Provider Queries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07502 - Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26368 - JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06625 - HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07563 - Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08303 - Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07209 - Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07948 - Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07355 - VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07987 - Loud and Clear: Dynamic Activation Steering for Improving Speech Intelligibility in Noisy Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07647 - Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.02115 - Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07774 - Identifying Introspection From the Inside Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07186 - Provably Tractable NFA-Constrained Language Generation via HMMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40185 - Stabilizing language models under continual learning via condition-anchored distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06940 - From Evidence to Action: How Tool-Using Agents Fail Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07753 - EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06956 - Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22954 - In With the Old: Enhancing 'Classical' Document Automation with Generative AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07480 - Cross-Lingual Activation Steering for Multilingual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16390 - Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02655 - Cross-Cultural Value Attribution in Large Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09945 - Penalty-Framed No-Valid-Option MCQA: Analyzing LLM Abstention under Invalid Choices Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08153 - Verifiable, Articulable, and Tacit Components of Preference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03025 - No Transformer Beats Six Covariates: Long-Horizon Prediction of Depressive Symptoms from Childhood Essays Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07764 - A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04898 - VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03203 - Holdout Best-of-N: Unbiased Evaluation and Its Cost Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08719 - Towards In-Parameter Memory Augmentation for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08630 - Too Categorical to be Human: Emotion Concepts in LLMs and Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.05880 - Are Language Models Script-Aware? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08037 - When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07715 - VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26189 - Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01103 - OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07847 - GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07046 - Sherpa: Teaching LLMs to Teach Adaptively Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08778 - Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07657 - Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07722 - AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17645 - Evolving language compositionality in a frequency-structured meaning space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29642 - Model in Distress: Sentiment Analysis on French Synthetic Social Media Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18226 - TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07224 - DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08085 - Disentangling Models from Personas in Heterogeneous LLM Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07535 - Kurate: Scalable Scientific Quality Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07306 - STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08208 - Benchmarking candidate coverage and rejection policy transfer in typed decision models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03387 - DLoop: Looped Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07659 - Monte Carlo Estimation for KV Cache Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07643 - The Missing Minimal Pair: Stereotype Evaluation in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08747 - Strong Multilingual Privacy Tagging at Encoder Speed Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38630 - Incidental information contaminates patient notes and disrupts clinical reasoning in large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08585 - Improving Diversity in LLM Short Story Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06729 - Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08231 - InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08604 - Emotion Recognition in Sign Language Conversation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23328 - FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.10020 - Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08513 - LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07580 - Inductive Claims Extraction at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05275 - Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33155 - Small Frequency Corrections Can Change What Survives KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27128 - Quantifying the Generation Modality Gap in Speech-Text Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14743 - Responsible Institutional Analytics: Interpreting Bias with AI Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07205 - Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08300 - A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02970 - Harness Engineering for Software Engineering via Modular Executable Dev-Primitives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07832 - Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20791 - SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04875 - The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08026 - Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07700 - IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08781 - ARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric Authoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07902 - Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08675 - JudgeMoE: Distributional Aggregation for LLM-as-a-Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07109 - Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07936 - Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.01732 - How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08544 - Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16017 - Structured but Silent: Probing Capability Requirements in LLM Hidden States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08018 - Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07519 - The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08162 - HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08063 - Unbiased Reward Modeling from Implicit Feedback for LLM Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23184 - SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech Separation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07047 - Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.08125 - UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09815 - When Does a Second Model Help? Cross-Model Review in LLM Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01471 - Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08448 - Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10162 - Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08095 - Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06650 - Quality-Aware Self-Correcting Speech Translation on an Edge Device Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07545 - When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12922 - Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14089 - SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08093 - Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08388 - Generative AI translations in high-stakes emergency messaging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08601 - ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29102 - AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01108 - A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07626 - Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08660 - KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38480 - Zero-Shot Lombard Speech Synthesis with Controllable Style Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12966 - Nucleus Speculative Decoding: Plausibility-Aware Verification Beyond Exact Distribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07822 - Hybrid Latent Attention for Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07940 - WavePrune: One period is often enough for RoPE Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06963 - Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20658 - Quantifying the Gap between Understanding and Generation within Unified Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02140 - WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02651 - Understanding Errors in LLM-Based Question Answering over Imperfect Tables Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04687 - Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07587 - Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06962 - Optimal bound for the polynomial Littlewood-Offord problem Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.08708 - Diverse Motion Customization via Control-based Dynamic Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07911 - APEX: Active Protection at Execution Boundaries for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06966 - Decoupled Multi-Agent Orchestration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07556 - How Children Design and Reason about Trustworthy AI Chatbots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25244 - Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06885 - COMPASS: Finding Where Reasoning Lives in Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07469 - OTel: Open Telco AI Datasets, Benchmarks, and Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07766 - WAMJET: A Harness for World Action Model Acceleration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03797 - Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08482 - SWE-Game: Can Coding Agents Build the Games We Want? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33678 - ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07460 - Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07081 ## Community - Quoting Ben Affleck Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/7/ben-affleck/ - Claude Haiku 5.5 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/7/claude-haiku-5-5/ - Anti-Patterns in Software Blogging Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/7/anti-patterns-in-software-blogging/ - Quoting Jake Boggan Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/7/jake-boggan/ - OpenAI “rogue” agent activities found on Wikimedia projects Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/7/openai-rogue-agents-wikimedia/ - I'm not paying $20 for ChatGPT or Claude because a free local LLM does Source: hacker-news Topic: General (+AI) URL: https://www.xda-developers.com/im-not-paying-20-for-chatgpt-claude-or-gemini-because-a-free-local-llm-does-everything-i-need/ - Claude Haiku 5.5 Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/claude-haiku-5-5 - GPT‑6 and Intelligent UI for everyone Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/gpt-6-for-everyone/ - Show HN: Agent.reviews – Where AI agents read and write reviews on tools Source: hacker-news Topic: General (+AI) URL: https://agent.reviews/ - OpenAI says teens use ChatGPT for under 15 minutes a day Source: hacker-news Topic: General (+AI) URL: https://www.reuters.com/business/media-telecom/openai-says-teens-use-chatgpt-under-15-minutes-day-worries-over-risks-grow-2026-10-07/ - Write Like It's 1866: LLMs Relearn Telegraphese Source: hacker-news Topic: General (+AI) URL: https://fiveminutesforward.com/post/2026-10-04-telegraph-test/ - LLMs and Data Poisoning Are Weaponized to Manufacture Consensus Source: hacker-news Topic: General (+AI) URL: https://medium.com/@eslam.elsewedy/synthetic-truth-how-marketing-power-and-ai-bend-reality-cd8a1173b968 - Show HN: TerrainSR – fast, realistic heightmap upscaling model Source: hacker-news Topic: General (+AI) URL: https://huggingface.co/joe-gibbs/terrainsr ## Media - Build & connect an incident investigation agent with Elastic Agent Builder and Gemini Enterprise Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=HQqb_TmrMCc - How voice AI agents control your browser Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=xDL5DFMo1-Y - HF Buckets: Upload Only What Changed with Xet Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=1E0ZoktFerQ