TILens Daily Edition 2026-11-11 Filters: topic=ai-research, github=hidden Stats: 749 articles, 8 sources, 741 research papers Top topics: AI, AI Research, Information Retrieval ## News - 😸 WATCH: AI Changed More in 4 Years Than You Remember Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/watch-ai-changed-more-in-4-years-than-you-remember/ - United Is Blocking AI Agents. The Fight Is Over Who Owns You(r Data). Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/united-wants-you-to-book-the-flight-your-ai-agent-isnt-invited/ - The Dark Edition of my new book is now available on Amazon! Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/the-dark-edition-of-my-new-book-is - Google’s AlphaGenome 2 Wants to Find Where Disease Begins Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/googles-alphagenome-2-wants-to-find-where-disease-begins/ - 😸 3 AI labs shipped for you Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/3-ai-labs-shipped-for-you/ - Can AI Use Math to Catch Security Bugs? Google Put It to the Test Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/google-ai-math-signal-security-verification/ - Everything That Happened in AI Today (Wednesday, November 11, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-november-11-2026/ - Google, Anthropic, and OpenAI Are Turning AI Assistants Into Workspaces Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/google-anthropic-openai-ai-assistants-workspaces/ ## Research - Using wearables to enable cardiovascular-kidney-metabolic (CKM) risk profiling for personalized coaching Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/using-wearables-to-enable-cardiovascular-kidney-metabolic-ckm-risk-profiling-for-personalized-coaching/ - “Are You Sure?” Flipped Qwen2.5-1.5B’s Right Answer 2 Times in 3 Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/are-you-sure-flipped-qwen25-15bs-right-answer-2-times-in-3/ - AI Assistant vs. Copilot vs. Agent, and When to Use Each Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/ai-assistant-vs-copilot-vs-agent-and-when-to-use-each/ - How to Use Apple's fm CLI to Run On-Device LLMs From Python Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-use-apples-fm-cli-to-run-on-device-llms-from-python/ - A Jev of All Trades: Build and Train a Jev-style Decision Model From Scratch Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/a-jev-of-all-trades-build-and-train-a-jev-style-decision-model-from-scratch/ - Margin-Guided Token Credit for Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14015 - On the Spectral Estimation of VARMA Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13973 - Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24001 - TimeSeek: Multi-Task and Multi-Domain Pretraining for Generalized Time Series Analytics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14491 - Target Selection with a Disappearing-Stimulus Mixed-Reality P300 Interface: Feasibility and Object-Distinguishable Versus Uniform Cues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13906 - Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14083 - Topology-Aware Reinforcement Learning for CAD Decomposition toward All-Hexahedral Meshing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12930 - Sanity Checks for Attention Surgery: Null Models and Matched Interventions for Representation-Motivated Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13543 - Making Strides in Symbolic Imitation Learning: Offline Demonstrations, Online Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13182 - Structured Confidence Perturbation via Fisher Geometry for Adversarial Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14046 - Metamorphic testing of learned AC optimal power flow surrogates reveals representation dependence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13566 - Decentralized Ranking Aggregation via Gossip: Convergence and Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22847 - Density-Ratio Losses for Post-Hoc Learning to Defer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19557 - Differentially Private Verification of Distribution Properties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10819 - Minority Reports: Balancing Cost and Quality in Ground Truth Data Annotation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.09341 - Continuous 3D Spatial Transcriptomics Reconstruction via Histology-Informed Implicit Neural Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14129 - VC-Dimension and Generalization in Geometric Machine Learning with Applications to Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13337 - Entropic Risk-Aware Monte Carlo Tree Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17667 - Understanding Sample Efficiency in Predictive Coding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11911 - Diffusion models for the $O(3)$ nonlinear sigma model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39568 - Tabular Foundation Models vs Tuned Gradient Boosting for Telecom Churn: A Profit- and Calibration-Aware Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12942 - Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14514 - Universal Approximation Theorem for Metaplectic Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13991 - Attribute-Evidence Learning with Multimodal Prompt for Generalized Category Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12975 - StatPrompt-LLM: A Lightweight Statistical Refinement for Foundation-Style Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12974 - Market-Conditioned JEPA: Learning from Unpredictable Market Shocks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13572 - Recurrent Modular Structure in Spiking Neural Network Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14262 - Diversity Curves for Graph Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06466 - Nonadaptive One-Sided Testing of Binary Rank Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14163 - Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14493 - Plumbline: When the Loss Lies, Validating LLM Training Correctly Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13393 - Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19181 - Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13916 - Differentiable Learning of Lifted Action Schemas for Classical Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13282 - PSL-RGHA: Parallel Split Learning with Reference Gradient Half-Space Alignment for Mitigating Gradient Divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14312 - Multi-Future Drafting: Mixture Block Drafters for Tree-Verified Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13017 - Train High, Ship Low: Efficient LoRA Synchronization for Distributed On-Policy Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13306 - Beyond local reconstruction: Geometry-preserving output alignment for binary LLM quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21651 - Evidential Deep Learning with conditional entropy for glaucoma detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13513 - Cold-Start Personalization via Bayesian Adaptive Questioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15012 - Bootstrapped On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13680 - Verifiable Agentic Traffic Class: A Policed Quality-of-Service Mechanism for Agentic AI Traffic, Evaluated from Simulation to Real-Kernel Adversarial Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14211 - Synapse-Control: Making Agent Experience Actionable with Lightweight Runtime Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13615 - Right for the Wrong Reasons? Evaluating Plausibility and Behavioral Change in Explanation-Guided Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14134 - FUTON: Fourier Tensor Networks for Implicit Neural Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13414 - Beyond the Log-Linear Frontier: Pre-Asymptotic Analysis of Finite-Budget Neural Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13534 - Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.16915 - Wrong the Same Way: Cross-Prompt Sharing Both Suppresses and Amplifies Reward Hacking in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13218 - Textual Response-Aware Guidance for Zero-Shot Adversarial Robustness of Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40309 - LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40063 - Neural Network-Assisted CLEAN for Efficient Multipath Parameter Estimation in MIMO Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13298 - MADSNet: A Multi-Scale Axial-Attentive Dense Spiking Network for Spike Camera Image Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12980 - Train on prefill, monitor at decode: Using sparse autoencoders for topic monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12935 - EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Model for EEG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08861 - IntentTwin: Deconfounding Candidate Support and the Oracle-to-Deployment Gap in Offline Web Behavior Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12918 - Where to Approximate in Neurosymbolic Inference? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13862 - Adaptive Reparametrized Time for Score-Based Diffusion Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02137 - Compute-Optimal Scaling Laws for Spiking Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15146 - One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13001 - Acceptance-Aware Draft Model Training for Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24150 - Permutation-Based Pre-trained Model Merging via Reciprocal Orthogonality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13016 - Iterative Orthogonalization Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04005 - CP-MLPs: A Tensor-Rank Theory of Tied and Untied MLP Blocks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13647 - ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12956 - Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27932 - LUMIR: Decoupled Multimodal Representation Learning from Heterogeneous Data for Next-POI Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14004 - Auditing Cross-Lingual Fairness in Language Model Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20047 - Show, Don't Tell: Detecting Novel Objects by Watching Human Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12751 - BODYinTRANSIT-Lab: A Multimodal Dataset for Investigating Sensory-Driven Transformations in Body Perception and Affective Experiences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14093 - On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21622 - A Theory of Cross-Validation Variance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14463 - Linear Probes to Bayesian Manifolds: Geometry of Arithmetic in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12998 - Muon Makes the First Mixture-of-Experts Layer Harder to Balance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37914 - Frequency Domain Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24969 - Time Series Change Point Detection with Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13295 - VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13150 - Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13596 - Is Online Linear Optimization Sufficient for Strategic Robustness? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12253 - The Star Geometry of Critic-Based Regularizer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.16852 - Mechanistic Interpretability of Deep Neural Networks: Methods, Frameworks, and Perspectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13868 - Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12798 - Settling the Burn-in Gap: Sharp Risk Bounds for Tail-Averaged SGD in Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13383 - BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25136 - CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.32012 - Volatility Heredity in Multivariate Time Series: A Statistically Guided Temporal Convolutional Approach to Variable Ordering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07746 - Reconstructing Boundary Layer Wind Profiles with Machine Learning: A Comparative Study on IGRA Radiosonde Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13359 - REAL Loss: Optimizing Real Expected Acceptance Length for Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14399 - Branch-and-Commit for Frozen RL Agents: When and Where to Spend Test-Time Compute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13003 - QAdapt: Noise-Adaptive Neural Pre-Decoding for Surface-Code Quantum Error Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28422 - Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13997 - From AGI to ASI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12683 - Robustness Verification in Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.13441 - Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13992 - Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13742 - Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11652 - Deterministic, Reproducible Inference in Exact Integer Arithmetic, and Verifiable Distributed Inference as Its Consequence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13730 - MouldIt: Data Efficiency of Multi-Task Temporal Representation Learning in Injection Moulding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13646 - You Don't Need Feature Learning to Do In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13431 - Nominate-then-Adjudicate: LLM-Assisted One-Pass and Per-Instance MIP Solver Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29391 - Denoising data using convex relaxations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02327 - Discovering Equations for the Thermodynamics of South Asian Monsoon Precipitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14401 - Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32797 - XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04171 - AI-Mediated Communication Can Steer Collective Opinion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16245 - Learning from First Discrepancies with Joint Reset and Pilot Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13913 - Accurate predictions of properties of energetic materials with tabular foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14462 - The Dose Makes the Poison: Exposure-Aware Evaluation of Generative Drug Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13398 - Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12955 - Looping Deeper Without Growing the KV Cache: Recurrent Depth for Causal Encoder-Decoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13378 - Reinforcement Learning based control of Cancer Chemotherapy treatments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12940 - JAX-WAVE: A Differentiable Physics-Supervised Framework for Inverse Wave Design in Heterogeneous Media Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13826 - AutoScaffold: AI-Guided Scaffolding for Reinforcement Learning of Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14515 - RamanPFN: A physics-guided spectral foundation framework for in-context learning across diverse Raman applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02157 - Stylization as Geodesic Navigation on Diffusion Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14097 - What a CAGE 4 Score Measures: An Audit of a Learned Cyber-Defense Benchmark, Its Reference Defenders, and the Tables Built on Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14068 - Enforcing Axioms for AI Alignment under Loss-Based Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13369 - Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14425 - Generative Online Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02581 - Data Density Scaling Laws for Image Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19013 - Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13213 - Opportunity-Cost Option-Critic: Adaptive Switching Costs for Robust Hierarchical Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14099 - Optimal Last-Iterate Bounds for Nonexpansive Stochastic Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13846 - GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10201 - When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14326 - Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15507 - ForeSpark: Joint Draft and Verification Budget Scheduling for Parallel Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13442 - Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2605.14786 - 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 - An Energy-Based Perspective on Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14383 - Emergent Biological Capabilities in a Foundation Model for Molecular Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14504 - Unipolar Neuron Networks Trained by Recirculation for Reward-Based Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14153 - DiffeoMorph: Learning Distributed 3D Morphogenesis with Rotation-Invariant Spectral Shape Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.17129 - INTENT: Out-of-Sample, Out-of-Time, and Cold-Start Evaluation on User Event Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13069 - Which Acoustic Features Survive Compression? Tracker-Estimated First-Formant Statistics for Codec-Robust Audio DeepfakeDetection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13258 - GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18556 - Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22010 - Compositional random forest Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14275 - Coding Agent Memory Post-Training II: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14009 - Domain-Routed Delta Optimization for Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13249 - Unified Optimization of Traffic Signal and Lane Channelization for an Isolated Intersection Using Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13599 - One-Sided Expert-Parallel All-to-All for Mixture-of-Experts Inference over NVLink Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13188 - LookThere! Sparse Vision by Reinforced Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04698 - Do Language Models Know Which Constraints Belong Together? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05726 - LoBoost: Model-Native Local Conformal Prediction for Gradient-Boosted Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22432 - HandsOnAid: Building and Evaluating an Offline First-Aid Assistant for Emergency Response Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14059 - Sharp Sample Complexity of KL-Regularized Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13480 - Variance Reduction for Decentralized Stochastic Optimization with Multiple Local Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41927 - Gradient Inversion through Linear and Affine Subspace Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13976 - Stochastic Projections and Rank-Aware Learning Rates for Federated LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13331 - Multimodal Model Diffing for Feature Discovery and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09928 - DEPUTYBENCH: Evaluating Contextual Safety in Enterprise Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13355 - Free Lunch Uncertainty: Sequence-Level R\'enyi Entropy from Particle Decoding for Adaptive LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13414 - Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process Critics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14374 - OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22979 - One Temperature to Rule Them All? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13077 - Massive Activations Confound Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13548 - Factor Augmented High-Dimensional SGD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19291 - The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05038 - REVELIO: Universal Multimodal Task Load Estimation for Cross-Domain Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.01642 - Exploring Post-Hoc Disentanglement of Audio Foundation Models for Music Similarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14415 - Near-Optimal Sample Complexity of Deterministic Agnostic PAC Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13210 - TorchCurves: Differentiable Parametric Curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14516 - Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13561 - The Unused Input: The Initial State as a Conditioning Interface for Recurrent TSFMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14357 - GigaEdge Spench: An SDK for Practical Streaming Speech Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13243 - FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02948 - MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13834 - Byzantine-Robust Muon: Resilient Momentum Orthogonalization for Distributed Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13137 - BioXArena-Pro: a research-grade benchmark for autonomous biomedical machine learning agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13994 - Seeing Isn't Enough: Unlocking Visual Reasoning by Bridging the Reasoning-Access Gap with TIGER Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10552 - Do Location Encoders Capture Spatial Effects? A GeoShapley Benchmark Across Scales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23453 - Evolutionary Computation: A Paradigm of Natural Generative AI and Creative Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08590 - EvoSurv: Evolution-Aware Multimodal Survival Modeling Reveals Complementary Prognostic Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13190 - TransferBreaker: Breaking Adversarial Transferability in Fine-Tuned Speech Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09109 - STABLE: A Continual Learning Optimizer with Adaptive Drift Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10655 - Deep Personalization: Continuous Context Observation for Local Proactive Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13457 - PARDIG: Global Precipitation Estimates Learned from Sparse Satellite Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13941 - Allocating Human Oversight in AI-Enabled Analytics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12497 - Multifidelity Operator Inference for Non-intrusive Model Reduction under Data Scarcity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13624 - HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14136 - Gaussian mixture models in Hilbert spaces via kernel methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05996 - From Architecture to Output: Testing the Structural Origins of Hallucination and the Amplifying Role of Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07537 - Counting Under Disagreement: Dollar-Weighted Measurement, Selective Machine Labelling and Budgeted Human Review from Disagreeing AI Readers of Administrative Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13215 - Personalized Affective Perception via Continual Learning in Human-Agent Negotiation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14247 - DUO: Dual Readouts of Diffusion Models for OOD Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13304 - Block-Sparse Gauss-Newton Optimization of Finite Basis Physics-Informed Neural Networks: Sparse Automatic Differentiation Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13231 - Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24490 - Self-Improving Training & Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21343 - Knowing When to Intervene: Causal Evaluation of AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09792 - When Does the Real Wiring Win? Testing connectome structure-function claims against unmeasured physiology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14508 - Fade to... Red? Scheduling Coloured Noise Exploration Supports Efficient Robot Learning with Reduced Movement Jerk Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11868 - Which Successes Make Good References? Action-Sequence Alignment for Multi-Turn On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13135 - EEGDash Corpus: A Training-Ready Public Corpus for EEG Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06356 - ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14492 - Advancing Mass-Conserving Deep Learning for Distributed Hydrologic Modeling: A Case Study in a Snow-Dominated Watershed Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13346 - SepsisFlow: an event-stream foundation model for continuous risk warning and trajectory modelling in ICU sepsis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13661 - FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02060 - ORCA: Hunting Compositional Failures in Text-to-Image Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09841 - Continual-ARC: Measuring Skill Acquisition over a Working Lifetime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14505 - Pruning and Distilling Mixture-of-Experts into Dense Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28207 - UGG: Unified Generative Geometry Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14440 - On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02340 - Physics-Constrained Autoencoder for Interpretable Health Representation Learning in Turbofan Engines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14266 - Query Complexity of Learning Axis-Aligned Partitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35495 - SplitLite: Low-Rank Residual Compression for Split Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23018 - On the Potential of Graph Neural Networks as Metamodels for Supply Chain Optimization: Dataset, Architectures, and Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16769 - Closing the BF16-FP16 Convergence Speed Gap in RL Post-Training with Stochastic Rounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13545 - Minimax Rates and Spectral Distillation for Tree Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11841 - Audited Gradients, Anchored Policies: Model-Based Reinforcement Learning for Efficient Flow Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13203 - LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38166 - Mixed Signals: Weight-Space Programming for EEG and ECG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13758 - Exploiting Feature-invariant Scaling Laws for Efficient A/B Experimentation in Recommendation Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13539 - One Trajectory, Two Requirements: Accuracy and Local Stability in Euler Sampling for Flow Matching Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13311 - Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02977 - Decode Token Parallelism: Memory-Efficient Distributed Attention Parallelism for Scalable LLM Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13293 - Prediction-Powered LLM Ranking with Adaptively Collected Human Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13186 - The Rise of Low Precision Floating Point Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00301 - Fermat ProbCover: Coverage-Based Active Learning on Fermat Distance Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13448 - Counterfactual Analysis of Extent Leakage from Annotation-Derived Prompts in Vision-Language Medical Image Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13970 - Weighted-AoI-Driven UAV Trajectory and Reporting for Dynamic CKM Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13726 - On Compatible Generalization Bounds of Deep Residual Networks From a Dynamical System Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20921 - Actionable Feedback: Improving Model Capabilities from User Edit Data on Clinical Documentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12904 - RB-LDC: Redundancy-Balanced Latent Coding for Noise-Robust Diffusion Latents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13955 - Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13514 - High Probability Risk Control for Online Policy Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13163 - ST$^2$U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23034 - Learning Perturbation Robust Policies for LLM Agents with Stable Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34064 - SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09745 - Outliers and the Hard-Margin Linear SVM in High-Dimension, Low-Sample-Size Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13869 - Stand-In Effects and Pooling Amplification: Lessons from Biological World Models for Testing Action Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01666 - AnchorMTS: Multi-View Signal Representation and Forecast-Anchored Fusion for Long-Term Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13794 - Affine Tracing: A New Paradigm for Probabilistic Linear Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10566 - AdjointFlow: Accelerating Scientific Inverse Problems with Physics-Based Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13389 - Machine-learning decoders for fusion-based quantum computing in real time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13630 - Alchemically Transferable Parameters for Variational Quantum Eigensolvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11445 - ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14035 - Chem World: A Large-Scale Benchmark and Physics-Aware Framework for Trustworthy Molecular Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13945 - Federated Learning for Cross-Regional Epidemic Forecasting with Asynchronous Outbreaks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14272 - CUVE: Making Supervised Classification more Accessible through Visualization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14098 - Bayesian inverse problems and epidemic-threshold uncertainty for a heterogeneous SIS reaction-diffusion model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14468 - Equation Recast for Canonical Operator Learning Across Parametric PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02982 - FedVP: Federated Learning across Heterogeneous Models by Pooling Locally Trained Verifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13708 - DnNP: Denoising Input Uncertainty in Neural Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14424 - Parallel Broyden Methods for Efficiently Evaluating Nonlinear State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13523 - GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01128 - Hierarchical Graph Representation Learning with Pooling-Induced Substructures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14126 - Discrete Model-Based Diffusion for Combinatorial Optimization in Multi-Robot Task Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13382 - Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14263 - Are Causal Neuron Circuits Unique and Transferable? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13885 - RANSAC Scoring Done Right Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27385 - Do we really need the Rademacher complexities? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.15118 - Generalizing Causal Decision-Making: Markov Equivalence, Transportability and Counterfactuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14066 - The Shape of a Program: Path Signatures for Trace-to-Program Induction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13005 - Bandit Profit-maximization for Targeted Marketing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.01361 - Safe Approximate Nonlinear Model Predictive Control Without Expert Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24503 - HiCAP: Hierarchical Cultural Adaptation via Personality for Dialogue Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13207 - Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.04898 - Everything in its right place: attention is a radio head Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13146 - Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07396 - Geometry-Dependent Approximation and Stability Properties of Shallow ReLU$^k$ Networks on Bounded Euclidean Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13952 - Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02126 - Self-Modeling Interventions can Modulate Emergent Misalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23700 - SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14246 - IC-GNN: Modeling Individualized Brain Community Organization for Disease Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13070 - Distribution Shift Detection in Remote Sensing Imagery using Machine Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13510 - One Policy for 100 Household Tasks: Our Solution for the 2026 BEHAVIOR Challenge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14432 - Third Eye: Beyond Immediate Gains in Recursive Self-Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12988 - Auditing the Judge: Internal Signals for LLM Reasoning Assurance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14323 - Partition, Refine, and Detect: Preserving Novel Category Capacity in Open-Vocabulary Object Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12976 - Explanation-Aware Fairness Beyond Output Parity: Joint Output-Attribution Regularization for Medical Image Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13052 - Causal Concept Explanations for Deep Neural Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14407 - Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18298 - Data Quality Challenges in Multimodal Tourism Recommender Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13972 - SpecValley: Aggregation as Spectral Valley in Dense Heterophilic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14176 - Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36202 - Where Do Vision-Language Models Get Left and Right? Position-Code Counterfactuals in Qwen2.5-VL, Qwen3-VL and InternVL3 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14060 - Machine Learning to Predict Digital Frustration from Clickstream Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20438 - Adaptive Policy-Guided Error Mitigation (APGEM): A Unified Learning-Based Framework for Noise Resilience in Quantum Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13815 - CroCoMAE: Cross-modal self-supervised collaborative representation learning for SAR-optical remote sensing data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14124 - Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08541 - Building World Models from Intrinsic Motivation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13113 - Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12964 - Beyond Interaction Scores: Selecting Feature Interactions via Independent Replication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13765 - Bursts That Outlast Themselves: Persistent Degradation in Prefix-Cached Agent Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13412 - An ensemble of graph generative models for assisted history matching of the Brugge field case Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12927 - Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38851 - RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06639 - XAI-Driven Confidence Estimation for OOD-Resilient Runtime Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13199 - XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12067 - Differentially Private Statistical Inference for Rankings from Pairwise Comparisons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13485 - Tabular Foundation Models in Financial Predictions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13550 - A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14397 - An Analytical Model of Compute-limited Multistage Training Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13276 - Continuous-Time Set-Transformers for Asynchronous WiFi-IMU Indoor Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13057 - MSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24395 - MMDM: Measuring Massive Multitask Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14309 - On Federated Averaging with Partial Participation under a General Variance Condition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14239 - Machine Learning-Based Reconstruction for Resistive Silicon Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11585 - When Covariance Is Not Enough: Kernel-Based Regularization for Single-Cell Counterfactuals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13748 - TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13714 - How Post-Training Influences Verbalized Algorithmic Computation in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13552 - Effective Biological Representation Learning by Masking Gene Expression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31562 - Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05355 - MammothDP: Private Boosted Decision Trees Ready for Trusted Hardware and Leakage-free Hyperparameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14317 - MicroLens: Read, Trace, and Rewire the Residual Stream with Two Lenses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13322 - Adaptive catalyst discovery emerges from composable scientific intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13536 - RadRef: A Reference-Free Metric for Radiology Report Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13168 - Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12277 - A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08743 - ZeroPoint: Lightweight Energy-Based Decision Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12992 - Variance Reduction for Gradients from Diffusion Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21489 - SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13452 - Multimodal Graph Learning: A Survey of Models, Benchmarks, and Frontiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12990 - Off-policy Learning with Excursion Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13275 - Omni-JEV: Text and Dual-Stream Speech Decisions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13777 - When Are Predictions Enough? An Evaluation Protocol for Frozen Expert Composition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13356 - C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14469 - When Should Diffusion Language Models Reconsider Their Commitments? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11551 - COMO: Closed-Loop Optical Molecule Recognition with Minimum Risk Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23546 - Split and Bridge: Multimodal Generation via Diffusion Bridging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10441 - AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02875 - CASCADE: Constraint-Aware SCAffolded DEcomposition for Logical Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13820 - How Much of Your VLA Is kNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13160 - Benchmarking Stochastic Interpolants for Modeling Physical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26282 - Differential Diagnosis of Frontotemporal Dementia and Alzheimer's Disease using Generative Adversarial Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2109.05627 - Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23398 - TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10251 - MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09288 - Can Hindsight Critics Guide Delayed Actors? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11863 - The RSI Tax: When Recursive Self-Improvement Is Not Worth the Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13524 - GraphToolbox: A Configurable Framework for Controlled Benchmarking of Graph Neural Network Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24609 - Generative Learning on Manifolds for Probabilistic Seismic Performance Assessment and Structural Identifiability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12908 - Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30746 - Evaluating Compositional Generalization in Transformers: The Role of Composition Equivalence and Module Coverage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13498 - Decision-Focused Learning via Neural Optimization Layers for Battery-Assisted Grid-Import Smoothing in AI Data Centers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13694 - Post-OCR Correction of Mixed-Script Uzbek Text: Byte-Level ByT5 with an Empirical Homoglyph Noise Matrix Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13609 - The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15189 - Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14328 - Curriculum proof repair with learned counterexamples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13627 - Dual-Core Tensor Wheel Decomposition with Structure-Cached Acceleration for Tensor Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13938 - One Byte, One Token: Byteifying a 27B Hybrid-Attention LLM with Self-Generated Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13607 - Deep Double Q-learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.00275 - Total Variation Distance Estimation in Autoregressive Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19510 - Structured Kernel Surrogate Models for Multimodal Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13198 - Recasting Visual Language Models as EEG Foundation Models for Clinical Neurodiagnostics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05538 - D-TINs for Track-Sampled Ice Sheet Surface Reconstruction from Satellite Altimetry Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12894 - Leveraging Psychophysical Attentional Distribution for Gaze-Augmented Reward Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13477 - Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14511 - ASPIRE: An Agentic System-Identification Platform for Iterative Reasoning and Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13114 - Action-Guided Reachability for Deterministic World Models of Vision-Based Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08991 - A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35658 - BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09505 - A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference Resets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14467 - Counting Events, Not Seeing Them: Diagnosing and Repairing the Readout Failure in Video LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09949 - Simultaneous Near-Optimal Region Identification in Continuous Simulation Optimization: Minimax Complexity and Adaptive Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13489 - Tree-Ising: Repairing Language Models with Bit-Level Ising Edits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14210 - Automatic regularization for Kronecker product MMSE filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14932 - Multimodal Abstention That Preserves Acquired Correct Answers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14311 - Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09919 - Continual Instruction Tuning for LLM-ased Management of Continuum Resources Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10292 - Beyond Passive Imitation: On-Policy Mid-Training Distillation for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13855 - Agentic Symbolic Search: Approximating Solutions of PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20467 - Investigating Composite Modeling in Multi-Objective Bayesian Optimization for Scientific Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13565 - Cross-Modality Investigation on WESAD Stress Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.18733 - Normalizing Flows for Classical Simulation of Quantum Circuits in Phase Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14006 - MediPFN: Amortized In-Context Nuisance Learning and Inference for Causal Mediation Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13219 - TriSearch: Learning to Optimize Triangulations via Bistellar Flips Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30220 - FaST: Factored Synthesis of Transitions for Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13013 - Placing LLM Lookup Tables by Per-Layer Prefetch Deadlines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13413 - Preconditioned Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02337 - Continuous Horizon Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13228 - Low-degree lower bounds via almost orthonormal bases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09353 - CRAFT: Conflict-Resolved Aggregation for Federated Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21317 - Robust Flow Matching under Target Corruption and Label Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13324 - Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21139 - Conformal Risk Control for QoT-Aware Lightpath Feasibility Under Technology-Driven Domain Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13893 - SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13410 - A Computational Model of Teacher-Student Co-Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.02853 - Deviation-Aware Pretraining for Cardiovascular Disease Detection from Electrocardiograms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14141 - DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07401 - M\"obius Interaction Filtering: Order-Selective Spectral Regularization for Multimodal Humor Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12913 - Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13993 - ALTO: African and Levantine Tech-Facilitated Gender-Based Violence Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06706 - From Show Programs to Linked Data Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14037 - From Search to Decision: How Post-Training Shapes Information-Seeking Capabilities in Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14149 - FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14477 - Fairness-Aware Retrieval Optimization for Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.15790 - Activation-Guided Graph Retrieval for Cognitive Memory Reconstruction in Language Model Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13127 - Auditing LLM Pseudo-Label Distillation for Review Informativeness at E-Commerce Scale Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13797 - Beyond the Document: Compiled Context and Governed Agents for Any Work Product Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13055 - SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04961 - A Technique to Model Product Information and User Reviews (MPIUR) Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13361 - IFRS Compliance Verification: An Open Multi-LLM Benchmark and Content-Conditioned Ensemble Classifier Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13595 - Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13966 - Controllable and Content-Based Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.20938 - SHARP: Semantic Hierarchical Agentic Reasoning for Next POI Prediction with Dynamic Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14220 - StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14236 - SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.36991 - DocFS: File Systems as Agentic Reasoning Environments for Complex Multimodal Document Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.12957 - DOTRAG: Retrieval-Time Reasoning Along Paths Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.18760 - Point-in-Time Encoders for Earnings Calls Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14325 - OmniReview: A Large-scale Benchmark and LLM-enhanced Framework for Realistic Reviewer Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.08896 - Combining Relevant Expert Knowledge Using Mixtures of Feedback Fuzzy Cognitive Maps Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05664 - From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.13914 - Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.40658 - ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.22549 - Ontology-Guided Knowledge Graph Construction and Robust Evidence Retrieval for Indian Knowledge Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.14050 - Catch It Where It Happens: Real Time Error Correction During LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13107 - Semantic Chains: From Reachable Facts to Justified Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14252 - Visual Similarity in Adult Word Extension and Artificial Word Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14116 - The Left Ripple of Byte-Pair Encoding: Certified Lookbehind for Every Dictionary Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13061 - Inherited Weights: Measuring the Tokenization Premium and the Sovereignty Cost of Language Models for the Global South Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13441 - ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11306 - When does text encoding matter for language modeling? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14459 - Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14387 - Understanding Mixture-of-Experts Language Models Beyond Expert Boundaries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13975 - GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13028 - The Value of Memory in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31303 - Understanding and Tackling Label Errors in Individual-Level Nature Language Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.13297 - SELD: Detecting Silent Evidence Loss in Context Compression beyond the Answer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12903 - Projection-Free Evolution Strategies for Continuous Prompt Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13786 - A Concept-Based Interpretable Framework for Clinical Text-based Prediction via Token-Concept Attention without Concept Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13564 - DermaVQA-DAS: Dermatology Assessment Schema (DAS) & Datasets for Closed-Ended Question Answering & Segmentation in Patient-Generated Dermatology Images Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24340 - BioMem: Agentic Memory for Biomedical LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13426 - The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13058 - Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17558 - Dyship: Leveraging Acoustic Features For Speaker Relationship Classification From Dyadic Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14241 - Program-Aided Patchable Skill Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14019 - Can AI Agents Synthesize Scientific Conclusions in Health? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11337 - Measuring Definition Sensitivity in LLM Annotation of Social Science Concepts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13339 - An evidence-traceable benchmark of clinical reasoning in large language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13562 - T-SANDHI: Tone Sandhi-aware Adaptive Network with Decoupled Hybrid Injection for Low-resource Taiwanese Hokkien Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18194 - Repository-Context-Guided Image Understanding for Agentic Software Development Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13026 - You Are What You Read: Indian Political News Media Bias Dataset for Hindi Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13686 - WarBias: A Bilingual LLM Benchmark of Stereotypes About Internally Displaced People and Veterans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11284 - Representational Atoms in Neural Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14168 - Walrus Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13689 - Tracing Moral Foundations in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05437 - Multi-User Large Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08567 - TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13577 - Thermodynamics of words Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14039 - Prague Dependency Treebank -- Consolidated 2.0: Enriching a Complex Annotation Scheme Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24324 - Characterising divergence between heuristic and language-model ratings of mobile user interface quality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05423 - Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03720 - Do Language Models Feel the Sentiment? Investigating Emotion Vectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13744 - LLM Validation Makes Minimal-Pair Benchmarks Easier for Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13788 - Time as Structure: A Temporal Backbone for Extraction and Reasoning over Legal Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15270 - Towards Foundation Decision Models: Drex Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07854 - Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30608 - A Multi-Word Tokenizer for 204 Languages That Needs Fewer Tokens Than GPT-4o's, Including on English Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13059 - ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14364 - From Relevant Posts to Attributable Spans: Explicit Symptom Evidence for Depression Questionnaire Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12900 - Understanding Students' Rationales for AI-Mediated Cheating: An Instructor Perspective from Online Forums Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13358 - StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25379 - Linear-time Minimum Bayes Risk Decoding with Reference Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.04251 - Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14413 - Word-Level Alignment of OCR and Ground Truth under Zoning and Reading-Order Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13752 - Using LLM Agents to Evaluate Prosocial Interventions on Social Media Platforms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12922 - Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14480 - From Bias to Positionality: A critical grammar for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14079 - Do Reasoning LLMs Refuse What They Infer in Long Contexts? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08874 - Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13811 - Darmok: Championship Cryptic Crossword Solving via Constraint Tightening and Resilient Orchestration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13557 - STDec: Spatio-Temporal Stability Guided Decoding for dLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06330 - Building Comparative Motivation Profiles with Symmetric Belief Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08243 - POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13578 - Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35581 - Pair-Merge Tokenisation Is Hard to Approximate on Binary Strings and Strongly NP-Hard on Unary Datasets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13568 - Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14100 - Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12247 - BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15893 - Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12901 - FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02545 - MISO-BR: An Open Corpus for Misogyny Detection in Brazilian Portuguese Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14036 - Hearsay or Fact? How Framing and Elicitation Shape LLM Probability Updates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27745 - Orthographic depth at two scales, with English also matched for lexicon size Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13400 - AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22715 - Brasilidade: Measuring Brazilian Identity for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12906 - Beyond Fluent Responses: Finding User Dissatisfaction in Human-AI Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13894 - A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20394 - OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13675 - Breakdown of Autoregressive Multi-Step Reasoning Under Concentrated vs. Diffuse Attention Head Dropout Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14209 - What drives the emergence of symbolic mechanisms in large language models? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13270 - Seeing Is Not Believing: Counterfactual Lesion Erasure Teaches a Small Medical Vision-Language Agent to Report Only What the Image Shows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13006 - An Interpretable Stylometric Framework for Early Chinese Buddhist Translator Styles: A Case Study on the Attribution of Disputed Works of An Shigao Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13636 - Are Dense Rewards Worth Their Tokens in GRPO? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13560 - Tracing Psychometric Inference in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12937 - Mechanistic Interpretability Needs a Logic of Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14483 - MorfFlex: Handling Rich Morphology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24366 - PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13843 - Mobile AI Factory: Building Specialized Language Models for Your Mobile Device Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13509 - Mapping Instructors' Attitudes Towards Cheating with AI: An Exploratory Analysis Using Forum Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13366 - Latin American Studies since the 1980s: From Apocalyptic Dreams to Assimilationist Consolidation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13216 - Stagewise and interpretable emergence of inside-outside computation in Transformer-based language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14221 - Framing-Induced Vulnerability in Large Language Models: Evidence from Chinese News Headlines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13531 - Differentiable Filtering for Inertial Odometry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13517 - Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26119 - Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13845 - An AI Assistant for Automating Anti-Corruption Expertise of Draft Legislation Based on the TRACE Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14244 - Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12995 - EJAI: Judgment-Preserving Civic AI for Data Center Environmental Justice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13525 - Deletion Sensitivity Is a Property of the Model: A Three-Condition Measurement across Seven Open Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13223 - Agreeing on the Answer but Not the Reason: Measurement Limits of LLM Reasoning Failure Taxonomies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13140 - MNN-Pocket-0.3B Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12311 - Compute the Interactions, Not the Attributes: What a Fact Layer Must Supply in the Chinese Sexagenary System Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13597 - Text Generation in Low-Resource Languages Using Human-Curated Vocabularies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37105 - StakeBench: Evaluating Language Understanding Grounded in Market Commitment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26074 - AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14333 - Einstein World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26969 - 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 - One Sequence Is Enough: Fingerprinting Language Models from Fixed-Length Integer Sequences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14010 - khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13012 - AVCC: Audio-Visual Conversation Corpus for Turn-Taking Prediction with a Human Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13957 - Off-target posterior mass: A training-free diagnostic for fine-tuning spoken language diarization probes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13430 - Earlybird: Predictive Streaming Speech Recognition in 29M Parameters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14421 - Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10693 - PathXAI: Evidence-guided structured pathology reporting by transferable tissue segmentation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09117 - CulturalCrosswords: A Multilingual Benchmark of Answer Constraints and Grid Completion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10044 - EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14356 - FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11588 - On the information rate of phones, syllables and words Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13990 - Meet UD_Czech-PDTC: A Large and Genre-Rich Treebank in Universal Dependencies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24337 - PrefReward: Learning User Preference Matrix for Personalized Text Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21067 - TimeOmni-o1: Bidirectionally Coupling Time Series Foundation Models and LLMs for Multimodal Reasoning and Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12902 - Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11790 - Can Large Language Models Develop Gambling Addiction? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22818 - LandslideFM: A Foundation Model Towards Unified Landslide Perception and Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12936 - Trajectory-Regularized Distribution Distillation for One-Step Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12978 - TreeAgent: Structure-Aware Memory Agent for Processing Long Hierarchical Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13946 - TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31882 - Learning Beyond Rigid Manipulation with Hybrid Soft-Rigid Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.07787 - MOAI: Module-Optimizing Architecture for non-interactive secure transformer Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13641 - ExpertCrowd-SWE: Measuring Frontier Coding Agents on Expert-Authored Engineering Tasks in Unfamiliar Codebases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13246 - Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13685 - Agent Architecture Cost-Success Trade-offs: A Controlled Evaluation across Enterprise-Style SOPs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12953 - DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13142 - Toward Foundation Detection Models via Example-Based Grounding in EM-DETR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14518 - Curated endoscopic retrograde cholangiopancreatography images dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16759 - Ceci n'est pas une pipe -- Toward a Symbolic Solver for the Abstraction and Reasoning Corpus Using Evolutionary Computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13831 - On Private Knowledge Retrieval and Private Inference for secure multi-agent systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13696 - When Proofs Are Abundant, What Is a Paper For? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12943 - Model-Free Runtime Measurement of Task-Relevant Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14111 - ProofCoder: Continuous Reasoning for Automated Software Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14106 - Agent-Guided Discovery of Exchange-Correlation Functionals with Physics-based Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13329 - Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13713 - Decide, Ask, or Defer: Clinical LLMs under Incomplete Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04542 - Agent Benchmarks Stop Ranking Before They Run Out of Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13541 - Monitoring One Channel Is Not Communication Control: Causal Evidence for Adaptive Reallocation of Joint Message--Route Codes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12959 - Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14382 - MicroBT: Centroid-Guided Synergistic Learning for Multi-Modal Micro Brain Tumor Segmentation and Counting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13912 - Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21098 - AFNO: Universal Certifiably-Arbitrage-Free Operator Learning Framework for European Call-Price Surfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12899 - Unified Panoramic Geometry Estimation via Multi-View Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26368 - Tailoring Optimization Approaches with Domain Knowledge in Industry Process for Meta-heuristic Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13940 - Just AI Governance and the Forbidden-Boundary Principle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13007 - A Statistical Framework for Algorithmic Collective Action with Multiple Collectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06749 - TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12970 - Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16102 - AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12941 - Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30955 - PhysMoE: Fast Spatial Grounding with Single-Token Coordinate Representation in Modality-Decoupled VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13000 - Forethought: Verifiable Reasoning from Neurosymbolic Primitive Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04096 - Auditable Human-Agent Teams for Autonomous X-ray Experimentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12933 - FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02536 - Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13254 - Learning Where to Trust: Reliability-Guided Expert Routing and Velocity Gating for 3D Deformable Registration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36672 - Compile-Gated Lean Proof Refactoring with Enterprise Agent Practices: A Model per Step under a US\$3 Cap, Followed by Programmatic Rewrite Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13011 - Swanada: Split-Encoder Capability-Routed Conformer CTC and Sub-30 MB On-Device Speech Recognition Across Twelve Scripts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13814 - From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13960 - IIT Patna at "ICPR 2026 TVRID Competition on Privacy-Preserving Person Re-Identification from Top-View RGB-Depth Camera" Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12960 - Transparency Disclosures for Chain-of-Thought Monitorability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13873 - Veterans' Mental Health Crisis Severity Annotation: Do LLMs Agree More Than Human Experts? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10048 - Transformers Provably Learn Graph Search: Training Dynamics and the Exponential Power of Depth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13594 - W-ISA: Transactional Execution of Weight-Space Intervention Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13232 - Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02711 - TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05980 - Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14122 - A computational framework for understanding embodied plans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13669 - Topological Dynamics Under Non-Stationary Supervision: Persistent Homology of Neural Network Weight Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13701 - The Case for AI-Enabled Gate Monitoring as Farm Security in the UK: A PRISMA-Guided Review of the Evidence on Rural Crime, Livestock Predation and Farm Access Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13933 - CAppleNet: A Coordinate Attention-Based YOLO11 for Real-Time Apple Stem Cavity and Calyx Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13920 - Agentic AI Meets Formal Verification in the Era of Agentic Hardware Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13705 - Few-Step Streaming Video Generation via Condition Shifting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14033 - AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13710 - SplatLab: Autonomous Scientific Discovery for 3DGS Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30468 - Disentangling Multimodal Rotary Positional Embedding in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13334 - AgentScript-Eval: Benchmarking LLMs and Agents for Code Generation in an Enterprise DSL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13183 - Identifying Macro Causal Effects in a C-DMG over ADMGs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.01551 - Softness is something you also need! Why compliance helps control: information metrics of a passive walker with compliant ankle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13779 - Cognitive Multi-Agent Search and Rescue: Language-Grounded Hierarchical Reinforcement Learning for Collaborative Robotics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13161 - DrugCoding: A Scientific Programming Agent for Drug Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13651 - Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07342 - CLADE: Category-Level Answering from Deficient Evidence in Retrieval-Augmented Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14355 - Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00033 - Towards end-to-end LLM-based censoring-aware survival analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25399 - STAR: Semantic-Criticality Tiered Allocation of Radio Resources via Zero-Shot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13238 - How Hyperbolic Are Hyperbolic Vision-Language Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13384 - Veritas: A Verifier Generation Harness for Agent Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13336 - A Stage-Wise Explainable Pipeline for Arteriolar-to-Venular Ratio Estimation and Retinopathy Screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14013 - Satellite Pretraining Is Not One Thing: A Matched-Pair Study of Generic and Earth-Observation Foundation Models for Scene Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13849 - Broad-Persistent Advising in Interactive Reinforcement Learning via Latent State Encoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13712 - Domain-Invariant and Language-Model-Assisted Acoustic Side-Channel Attacks on Keyboards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13922 - Beyond the Mean Gap: What Transferred-Angle QAOA Retains on a Superconducting Processor Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10529 - Two Communities, One Problem: Branch-and-Bound vs. A* for Resource-Constrained Project Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14426 - ChipOmni: A General-Purpose AI Agent for Electronic Design Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13020 - An Augmented Lagrangian Approach to Lifted Bellman Linear Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14183 - Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07935 - Mitigating Private Data Leakage in LLMs with Whiteout Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02418 - IECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for Electrocardiogram Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28083 - Towards Scalable Network-Based Interventions for HIV Treatment and Prevention via R2C-Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13312 - CompressionBench: How can your coding agents compress LLMs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06858 - EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12934 - Understanding-First AI Engineering: Purposes, Reference Architecture, and Architectural Patterns for Human Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13022 - Are Spiking Neural Networks Harder to Steal? The Role of Stochastic Encoding in Model Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36298 - BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18598 - BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14171 - Beyond Proxy Metrics: MLLMs as Human Surrogates for Explainable AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13926 - AI Alignment Is Neither Solvable nor Sufficient Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13167 - Do AI Agents need Preventive Care? An Epidemiologic Cohort Design for Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13333 - BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04512 - Reliability of Claude Code as an Agentic AI Grading System for Handwritten University Exams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13217 - Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17561 - Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07948 - Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13262 - TAPCO-G: LLM-Guided Design-Adaptive Timing and Power Co-Optimization with Graph-Based Physical Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13931 - Accurate Predictions in Education with Discrete Variational Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23484 - Teaching the Harness: Student-Aware Skill Transfer for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13144 - The WoW: A Large-Scale World Knowledge Corpus for Full-Lifecycle LLM Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13487 - Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14419 - Integrating Action Prefix Prediction and Alignment Across Modalities for Multimodal Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13782 - Remote Sensing Change Detection via Weak Temporal Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02126 - Spectral-Convolutional Factorized Transformer for Joint Multipath Parameter Estimation: Applications to mmWave Positioning and Radio SLAM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01491 - Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14320 - DisasterAgent: An Evidence-Driven Agent for Verifiable Disaster Report Generation From Remote Sensing Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13776 - Code-Grounded Agentic Explanations for Static Analysis Vulnerability Findings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13041 - MAGAR: Multimodal Agents for GUI-Based 3D Mechanical Assembly and Minimal Rework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02472 - Graph Visualizations in Prompts for Knowledge Graph Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12938 - Data augmentation using generative networks to identify dementia Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2004.05989 - Achieving Robust Channel Estimation Neural Networks on Doppler effects by Designed Training Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14267 - Benchmarking LLM Next-Step Recommendations with Knowledge Space Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13667 - From Process Models to Composable Agentic Workflows: Combining BPMN, Agents and Enterprise Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13196 - Can KV Cache Be Reused Across Model Updates? A DeepSeek-V4-Flash Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14051 - LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14285 - Obscured Wildfire Flame Detection by Spatio-temporal Analysis of Smoke Patterns Using Frame-wise Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14074 - Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06190 - TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22639 - Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14260 - Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04785 - Looking One Step Ahead: An Anticipation-guided Agent for Object State Readout in Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14113 - ICLayout-Bench: Benchmarking LLM Agents for Custom Circuit Layout Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12982 - When Reasoning looks like Hidden Understanding: How Chain-of-Thought Fosters Anthropomorphism, Perceptions of Epistemic Superiority, and Cognitive Deference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13456 - AURA: Auditory Spatial Intelligence via a Unified Representation from a General-Audio Encoder through Complete Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13687 - A Dynamic Survey of Soft Set Theory and Its Extensions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21268 - Region-Wise Logit Fusion and Utility-Gated Refinement for Brain Metastasis Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13884 - A Hardware-Trained Generative Quantum Eigensolver for Sample-Based Quantum Diagonalization of Organotin Hydroxides up to 70 Qubits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13755 - Multi-Stage Phase-Aware Self-Supervised Reconstruction for Multi-Echo Gradient-Echo MRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13352 - The AI Era's Lines of Code? A Case Study on What an Engineer's Token Spend Measures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13396 - Explainable Iterative Data Visualization Refinement via an LLM Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15319 - TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13971 - SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12950 - AnalogRetriever: Learning Cross-Modal Representations for Analog Circuit Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23195 - Cross-Border Fulfillment Center Selection via Doubly Robust Estimation and Linear Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14174 - Interleaving anatomical inspection and diagnostic reasoning for explainable radiology report generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14018 - Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13388 - From Questions to Decisions: Benchmarking How LLM Agents Acquire Decision-Relevant Information from Human Beings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13015 - PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical Commonsense in Text-to-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13576 - Just Image Transformers with Late-Stage Pixel Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13120 - Multi-Agent Coordinated Rename Refactoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00482 - ProTEUS: A mutation-resolved world model for closed-loop protein evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13348 - Developing an Operational Model for an Internet of Data Based Trusted Data Space for Vocational Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13520 - A Comprehensive Survey of Agent Distillation across Models, Artifacts, and Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36630 - MRFoundry: Knowledge-guided agent loops for end-to-end MRI research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13289 - Nepali-English Code-Mixed Speech Recognition: Data Preparation and Adaptation of a Speech Foundation Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13512 - Token Importance-Aware Semantic Communication Enabled Robust Video Transmission Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12928 - Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13850 - MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26185 - Living constitutions: Participatory alignment for sovereign foundation models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13402 - Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14017 - MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Visual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01055 - Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09906 - Benchmarking Vendor-Guided Optimizations on Edge NPUs: From NPU Only to End-to-End Performance. Extended technical report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13563 - Scoped Semantic Invariance as a Foundation for LLM Reliability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33267 - Decisions by Discrimination: Differential Evidence for Medical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13233 - Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13801 - Relaxing Cross-Modal Correspondence for Multimodal Remote Sensing Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13807 - ZoomGain: Mining Global-to-Zoom Perception Gaps for Fine-Grained Visual Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14076 - Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.15253 - Multimodal Road Closure Mapping via Cross-Modal Graph Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13192 - A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14256 - Ninety-Six Ways to Measure a Scribe: Fragmented Evaluation of Ambient Scribes in Healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14284 - Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09767 - BuySideFlow: A Point-in-Time Benchmark for LLM Agents in Investment Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12966 - FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10285 - Trust, but verify, audit and attribute: a human-in-the-loop framework for checking AI-produced research results Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13042 - Medical Image Segmentation: Foundation Model Adaptation versus Task-Specific Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14519 - Elicitation of the parameters of a multi-criteria sorting model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13062 - An Open Implementation Flow for the Xilinx Spartan-3E and Spartan-6 that Runs in the Browser, Checked Byte for Byte Against ISE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13008 - Curie's Jarvis: Autonomous Robotic Chemistry Experiments from Printed Protocols Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13251 - Stinging the Swarm: Extracting Attacker Intelligence from a Twin-Controller OT Honeypot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13406 - Earth Embeddings in Environmental Remote Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13612 - Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13613 - Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13496 - NCP: Verifier-Guided Optimization of Weight-Space Control Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13236 - Purin: A Biology-inspired Mechanism for Artificial Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31235 - Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25891 - Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14196 - Agentic discrete-event simulation for manufacturing system design: an open 3D simulator, a benchmark and an industrial case Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10602 - Graph Attention-based Decentralized Actor-Critic for Dual-Objective Control of Multi-UAV Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.09195 - Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13504 - No finite rulebook can certify every safe program: an impossibility theorem for gatekeeping AI agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13367 - Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28063 - When Words and Bodies Disagree: Realizing Verbal and Nonverbal Mismatch Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22731 - Physics2Weight: Direct Neural Network Architecture and Weight Generation from Physical Laws Using Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12954 - CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15664 - GRAP: Gender Rubric-Aware Probing for Analyzing Gender Bias in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13024 - Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15265 - F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13325 - Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14487 - SeqFold: Timestamp-Addressable Compressed States for User Action Sequence Backbones Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13704 - Specializing Meta Multi-Objectivization as Baseline for Software Engineering Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12991 - Prune-and-Merge: Training-Free Scaling of Vision Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18039 - KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16682 - Autonomous Optimization of Numerical Algorithms by an AI Agent: Application to Atomistic Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13143 - APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13030 - TIB: Sample-wise Tempered Information Bottleneck for Multimodal Attribution beyond Alignment Assumption Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12997 - Low-Margin Branch Points in Deterministic LLM Deliberation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00546 - Direct Trajectory Optimization for Inference-Time Alignment of Text-to-Image Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11821 - SafeRoute-MAS: Coverage-Aware and Risk-Calibrated Message Routing for Multi-Agent Scientific Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13454 - Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14418 - Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06490 - Embodied Science Agents: Making Embodied Experimental Design Learnable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12958 - RBLA+: Efficient Rank-Specific LoRA Adapter Extraction for Federated Fine-Tuning with Heterogeneous Clients Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12961 - Key Institutional Considerations for Designing Effective Independent Verification Organizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10168 - Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10425 - With Tools or Because of Tools? Tracing Capability Gains in Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02357 - PegasusAI Studio: Legible Cyberinfrastructure and Accountable AI Agents for Scientific Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13309