TILens Daily Edition 2026-11-20 Filters: topic=ai-research, github=hidden Stats: 634 articles, 7 sources, 626 research papers Top topics: AI, AI Research, Information Retrieval ## News - A Mathematician Says Claude Helped Prove the Riemann Hypothesis Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-assisted-riemann-hypothesis-proof-claim/ - Google’s Gemini 4 Neon Ran Neck and Neck With Claude Code for Less Than Half the Cost Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/gemini-4-neon-claude-code-benchmark-cost/ - 😺 Meta's Muse AI Agent Reportedly Accessed Signal Messages Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/meta-s-muse-ai-agent-reportedly-accessed-signal-messages/ - Meta's AI Agent Read Private Signal Messages. How Did It Get Access? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/meta-muse-ai-agent-private-signal-messages/ - Hackers Used AI to Attack the European Commission. How Much Did They Automate? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/eu-commission-ai-cyberattack-artex/ - Copilotforce Gives Sales Reps a Better Way to Use Salesforce Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/copilotforce-salesforce-microsoft-copilot/ - Everything That Happened in AI Today (Friday, November 20, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-friday-november-20-2026/ - Why Nvidia’s Rumored Inception Deal Has Me Excited Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/nvidia-inception-acquisition-diffusion-ai/ ## Research - How Google Duplex evolved to also call businesses for you in Gemini Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/how-google-duplex-evolved-to-also-call-businesses-for-you-in-gemini/ - LightGBM vs. a Four-Week Average for Forecasting Bike-Share Rentals Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/lightgbm-vs-a-four-week-average-for-forecasting-bike-share-rentals/ - Clairic Hit 98% Accuracy on 72.8% of Questions via Confidence Scores Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/clairic-hit-98-accuracy-on-728-of-questions-via-confidence-scores/ - How to Prepare for a Credit Risk Internship Interview in Nine Steps Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-prepare-for-a-credit-risk-internship-interview-in-nine-steps/ - Five Guardrails That Limit the Damage an AI Agent Can Do Source: towards-data-science Topic: AI Research (+AI, FastAPI, Python) URL: https://towardsdatascience.com/five-guardrails-that-limit-the-damage-an-ai-agent-can-do/ - The Value of Information in Resource-Constrained Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24974 - GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39601 - Federated Learning of Car Aerodynamics Surrogates with Spectral Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25300 - Chameleon: Dynamic Format Adapter for Efficient Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33496 - What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12304 - Fast Gauss Sums via Flash Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04910 - Designing Algorithmic Recommendations to Achieve Human-AI Complementarity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.01484 - FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06404 - Probing the limits of materials design via a comprehensive crystal database of 14.6 million structures with 140 properties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32678 - Sparse corruption in low-rank matrix inference: the PCA benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.11927 - PriTabICL: Differentially Private Tabular In-Context Learning with Task-Aligned Cluster-Wise Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25073 - Gradients for Interventions and Activation Values for Detection: Targeted Feature Learning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32355 - Learning Which Evidence-Seeking Decisions Matter: Calibrated Counterfactual Replay for Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05263 - SCAR: State-Space Compression for AI-Based Radio Resource Management of Vehicular Services Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06243 - Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26442 - Active Learning For Contextual Linear Optimization: A Margin-Based Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2305.06584 - The sublevel Flood bifiltration: towards scalable 2-parameter persistent homology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05441 - Some Memories Must Fade: Persistence and Decay of User Memories in Model Parameters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25235 - Compact set-valued deep ensembling in multi-class classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05332 - Quantum Nondecimated Wavelet Transform: Theory, Circuits, and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21478 - Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14988 - HapBO: Harnessed $\alpha$-$\pi$ Bayesian Optimization via Expert Natural Language Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25100 - A Byzantine-Robust Federated Learning with Nesterov's Momentum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02657 - Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23862 - Towards Better Exploration in Sequential Test-Time Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39632 - Can Computation from Earlier Problems Help LLMs Solve New Ones? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39394 - SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09868 - PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29486 - Are We Grading Properly? Understanding Failure Modes in Medical Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16023 - Prior-Amortized In-Context Bayesian Inference for Generalized Linear Mixed-Effects Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24422 - Separating Interpretability and Reconstruction in Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25165 - Gradient Regularized Newton Boosting Trees with Global Convergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00581 - A Model of Diverse Sampling from Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25003 - Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21347 - Hierarchical Pooling for Sheaf Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20932 - Supportive Token Revealing for Fast Diffusion Language Model Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04236 - Mammography Foundation Models for Opportunistic Prediction of Major Adverse Cardiovascular Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19385 - Attention at Absolute Zero Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11937 - Physiological Trajectories and Observation Patterns in ICU Mortality Prediction: Transportability Under Changing Measurement Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.42126 - Where Global Context and Weight Sharing Work in Compact Vision Backbones Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23446 - On Agentic Manipulation Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09892 - When Objectives and Evaluators Disagree: Evaluating Transfer for Post-hoc Demographic Framing Mitigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25258 - Direct Topology Tracking in Continuous Implicit Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12157 - Intelligent Embedding Pruning for Large-Scale Recommendation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25288 - Rate-distortion Assessment for Hierarchical Content Summarization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25151 - When Is Program Structure Required? Certificate-Grounded Calibration of Program-Induction Difficulty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24975 - Learning with Local Search MCMC Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14240 - Channel-Dependent State Space Model for Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36453 - Does AI Assistance Preserve or Collapse Disagreement? A Study of Pre-Annotations in Ambiguous Video Labeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21798 - LLM Complexity: Towards a Computational Complexity View of Large Language Model Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24943 - Structured Role-Aware Policy Optimization for Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07274 - Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19153 - Risk-optimal active learning with informative abstention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24986 - Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18372 - Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19246 - MADJEPA: Enhanced Multi-Stage Joint-Embedding Predictive Architecture for Medical Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25194 - A Bayesian latent class reinforcement learning framework to capture adaptive, feedback-driven travel behaviour Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14713 - Improving On-board Shape Models Using Sun Sensors and Implicit Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24976 - Moving Generality from Model to Modeler: LLM Agents for PHM on a Deployment-Style Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25252 - Density Feedback Control for Transferability of Generative Sparse Adversarial Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25001 - SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01978 - From Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAgger Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25197 - From field-scale to large-scale spectral libraries: Tabular foundation models in soil spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00608 - Necessary, Not Sufficient, and No Longer Available: Grader Non-Determinism After the Withdrawal of Sampling Controls Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26185 - LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00240 - EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30293 - ConDR: Conservative Reachability through Neural Hamilton-Jacobi Subsolutions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06802 - Silver Rate Is (Almost) Optimal for Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09152 - Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.13711 - Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37789 - Survival of the fittest Cox model: Pivotal variable selection for time-to-event data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19374 - Learning to Verify: Signature-Guided Training for Adaptive Adversarial Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25271 - Scone: Symmetry-aware Neural Combinatorial Optimization for Graph Coloring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25273 - Learning to Read Events for Exact State Tracking with Frozen Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25211 - On the Impact of Feature Reduction Techniques on Adversarial Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25004 - Learning Multinomial Logits in $O(n \log n)$ time Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2601.04423 - CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.07807 - Variance-Optimal Counterfactual Policy Design for Sample-Efficient Online A/B Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24757 - RePAIR: Predictive Self-Supervised Representation Learning in Chess Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11860 - Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08015 - Bayesian $\kappa$-Explorer for Minimax Model Estimation in MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25160 - Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17794 - Fast and Memory-Light Evaluation of Density-Based Clusterings with the DISCO Index in R Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25114 - Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00310 - Variance Reduction for Matrix Computations with Applications to Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2106.14565 - {\lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23647 - Before the Choice: An Evidential Framework for Studying Prospective Representations in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25170 - Variance-Adaptive Upper Confidence Bounds for Multi-Armed Bandits with Kaplan--Meier Survival Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24988 - Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05608 - A human-in-the-loop Bayesian optimization framework for constraint-aware bioprocess development Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19230 - Infer3D: Inverse Generative Modeling Enables Robust 3D Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25061 - OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12075 - Rational Sparse Autoencoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14990 - Synthetic Neurosymbolic Task Generation with Controlled Constraint Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.19597 - LazyWeights: Decode-on-Demand Edge LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17108 - ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35174 - AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20643 - Every Measurement, Every Direction, All at Once: Multimodal Flow Matching for Molecules and Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22098 - Variational analysis of determinantal varieties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22613 - SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25301 - FlowMap-OPD: On-Policy Distillation for Few-Step Flow-Map Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37851 - Prediction with Foundation Models under Deployment Budgets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12466 - Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Optimal Bit Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35628 - The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07389 - Adaptive Inference for Resource-Constrained Dynamic Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03736 - Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09031 - Optimizer-dependent training dynamics converge to the same one-third optimal data scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37745 - CAIMS: Scalable Cross-Array In-Memory Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25141 - Empirical Variational Bayes Factorization for Longitudinal Matrix Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25065 - ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02363 - Learning from Transients: Linear RNN Scaling Laws in Stationary Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27964 - CHORUS: Coverage-Guided Agentic RL and Policy Consolidation for Testbench Stimulus Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10090 - FlowDrive: moderated flow matching with data balancing for trajectory planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21961 - Cross-Question Reliable Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25292 - Anytime-Valid Conformal Risk Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04364 - SynthDCB: World Distillation for Scalable Device Control Benchmarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18639 - Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22226 - The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09186 - GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39600 - {\phi}TD: Distributional Reinforcement Learning using Characteristic Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25208 - How many sorted projections determine any n points in k dimensions? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06470 - Near-Quadratic Sample Compression for All VC Classes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25011 - Characterizing High Bandwidth Flash for LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39131 - FlexTSF: A Flexible Forecasting Model for Time Series with Variable Regularities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23160 - Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05869 - Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35465 - BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22050 - Long-Range Video Presentation Attack Detection: A Three-Class Benchmark Across 1-100 m and Two Sensor Types Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25108 - Visual Jev: Accurate and Efficient Decisions from Shared Visual Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25845 - When Does Causality Help in Multivariate Time-Series Anomaly Detection? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15073 - DL101 The Representation Capability of Neural Network Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24980 - On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12107 - EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04417 - When Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16694 - PDE-State Conditioning for Learned Optimization Using Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25185 - SimVLA: Attributing Gains in VLA Models Through Controlled Ablation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18224 - Security of Deep Reinforcement Learning for Autonomous Driving: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2212.06123 - Blind Spots Travel, Knowledge Stays Home: What RL Inherits from an LLM Judge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25191 - Statistical, Machine Learning and Deep Learning Methods for Missing Covariates: An Empirical Evaluation with Applications to Alzheimer's Disease Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25219 - Convergence Rate of a Functional Learning Method for Conditional Stochastic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13048 - The Double-Edged Sword of Information: Revealed versus Hidden Lotteries in School Choice Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34074 - Game-Theoretic Data Allocation for Expert Specialization and Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25167 - ICARE: cross-domain text classification with incremental class-aware representation and distillation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24959 - Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11770 - Balance of Benchmarks: Evidence Retention and Multiplicity-Aware Model Comparison Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30044 - Storing the Gemma 4 K=V Cache Once: Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23035 - Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30117 - Best-of-Depth: Learning Exploratory Dynamics in Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04663 - Virasoro Symmetry in Neural Network Field Theories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24420 - Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09541 - Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17117 - Temporal Extrapolation of Elastic Seismic Wave Propagation in Layered Media Using Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25130 - BuggyMLE: Scaling Machine Learning Engineering Difficulty with Bug Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25088 - The Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06476 - DS3M: Deep structured state space models for nonlinear system identification on modern hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25274 - STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38169 - Learning Curves and Prediction Persistence to Under-Regularization of Spectral Algorithms in Large Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23212 - ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18088 - Stability Bands for Feature Attribution: The Core, the Nucleolus and the Bargaining Set of Explained-Variance Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25238 - Privacy-Utility Tradeoffs with Quantum Local Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10510 - Agnostic Smoothed Online Regression with Adversarial Responses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32478 - Paint-Anything: Unified Any-Color Control for Image Generation and Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20816 - Process-Knowledge-Guided Latent Diffusion for Generative Design of Porous Architectures: A Case Study in Aerosol Jet Printing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25264 - Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37351 - Hierarchical Latent Structure Learning through Online Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19139 - Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12830 - Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23445 - Xaurora: Generative Weather Forecasting with Denoising Stochastic Interpolants from a Foundation Model Prior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06509 - TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17170 - Auditing Learned Dynamics in Weather Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25119 - VESTA: Visual Exploration with Statistical Tool Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00384 - Classical Energies Learn to Reason 1,000x Faster than Looped Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17309 - Controllable Chains of Thought Can Reveal Less, Even Without Evasion Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21799 - LLMs Are Already Confidence-Aware Zero-Shot Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25289 - PsyWorld: Profile-Conditioned World Modeling for Human Behavior Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24999 - Generative Forecasting from Coarse Observations: Does Cascading Help? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00686 - Friction-Augmented Drifting Models for Resource-Efficient Domain Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18194 - Two Principles for Autoregressive Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02986 - KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30059 - REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.32113 - Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07385 - Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08963 - Continuous-time learning of probability distributions: a case study in a digital trial of young children with type 1 diabetes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24427 - Capturing In-Context Learning Dynamics with Task Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01054 - TabPFN: One Model to Rule Them All? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.20003 - Deconstructing Intraocular Pressure: A Non-Invasive Multi-Stage Probabilistic Inverse Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14167 - Watch Where You Linearize: Predicting and Correcting Model-Merging Interference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25000 - QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19513 - D\'ej\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02044 - Optimal algorithmic complexity of inference in quantum kernel methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15214 - Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05833 - Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06837 - Implicit Neural Representations of Individual Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12200 - Predicting Public Health Impacts of Electricity Usage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22031 - LQ-Rec: Late Quantization for Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.25256 - LSP-RAG: Latent Scoring Perspectives for Knowledge Graph Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.25229 - From transcription to semantic corpus analysis: unsupervised learning of sentence representations for ancient languages Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.24542 - Keep it Simple! A Multiple-Choice Task can Benefit Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.19320 - When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37358 - Beyond Dimensionality: Domain Shift and Catastrophic Forgetting in Single- vs. Multi-Vector Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.29519 - The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20050 - FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.25071 - Retrieving Patristic References and Modelling Topics in Bullinger's Reformation Correspondence Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.25247 - Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2502.16759 - MMIntentFlow: An Intent-Driven Real-Time Multimodal Search System with Image-Text Queries at Xiaohongshu Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.20448 - How to make a moral agent: sentimentalism and rationalism as lenses on AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18714 - Periodic and Harmonic Periodic RoPE for Length Extrapolation in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27980 - Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19149 - Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20158 - LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13451 - MUSE: A Full-Text Cross-Domain Knowledge Base of Scientific Problems, Solutions, and Rationales Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10974 - A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39027 - TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18061 - Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07532 - MosaicLeaks: Privacy Risks in Querying-in-the-Open for Deep Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30727 - PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20808 - Formalizing Formal Semantics: The Formal Atlas Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.19509 - SnapJudge: Multimodal AI Detection for Math-Heavy Scientific Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21062 - NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28481 - Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23788 - Agent as Policy for Robotic Manipulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12541 - Natural Language Processing: An Applied Research Practicum From Classical Text Processing to Multimodal and Agentic Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03799 - Robust LLM Evaluation with Boundedly Bad Judges: A Constrained Maximum Likelihood Approach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03257 - Living off the Local Model: Abusing Browser-Embedded Language Models for Post-Exploitation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25086 - Shortcuts or Memorisation? Revisiting Data Corruption in Natural Language Understanding with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16843 - Don't Lose Focus: Activation Steering via Key-Orthogonal Projections Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06342 - SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27786 - From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00172 - $\ell$BISG: Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06273 - The ROI of Small Examples: Optimizing In-Context Learning Under Token Budgets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24971 - A minimal probe of task modeling in language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02028 - Self-Rewarded Reinforcement Learning for Better-Structured Medical Explanations in Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24650 - TETHER: Training-Free, Elastic, ToC-Anchored Hierarchy Extraction and Recovery in Design-Driven Long Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24960 - MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18565 - CoMPASS: A Multi-Turn Benchmark for Measuring LLM Reinforcement of Parasocial Behavior Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25109 - Forget Freely, Grep Later: Lossless, Index-Free Memory for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25123 - Chorus: Shared N-gram Embeddings with Layer-wise Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23386 - CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24977 - Does Merge Form a Hopf Algebra? Coproducts, Traces, and the Prospects of Algebraic Minimalism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11502 - When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08236 - Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22610 - No-Harm-Jury A Jury-Based Multi-Dimensional Harm Evaluation Framework for Medical AI Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24972 - Steering Automated Scientific Discovery via Audited Epistemic Exploration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25214 - Polar: A Benchmark for Evaluating Political Bias in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12922 - Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15277 - Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22583 - MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02011 - LipSpell: A Language-Independent Phonetic Scoring Framework for Spelling Correction Combining Distinctive-Feature Edit Distance, Keyboard Geometry, and Corpus Frequency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24285 - Quantifying Cultural-Psychological Constructs in Four Centuries of Ottoman Court Registers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24981 - Global Importance Estimation for KV Cache Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24969 - Think Multilingual, Not Harder: A Framework for Analyzing and Teaching Code-Switched Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15490 - Geometric Factual Recall in Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12426 - Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24963 - HireWatch: Evaluating LLM Compliance with U.S. Employment Law Under Contextual Pressure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24970 - DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09185 - Harness-Zero: Harness Distillation via Agent-as-Harness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24974 - Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10592 - Mechanistic Interpretability Needs Philosophy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.18852 - HEDGE: Gated Hypergraph Memory for Scalable Multi-Agent Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38902 - Calibrated Decision Rewards: Training Language Models with a Judge That Knows How Sure It Is Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.25135 - Prompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11015 - EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20846 - EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30429 - What the model knows but does not say: monitoring medical LLMs through verbalized thoughts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24994 - Let a Small Model Read First: Faster Prefill for Long Interleaved Image-Text Inputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24431 - GLIDE: Scalable and Event-Aware Inductive Forecasting over Evolving Logistics Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23942 - In Situ Training of Optical Neural Networks by Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23875 - Measuring and Attributing Evidence Sensitivity in Medical Vision-Language Models via Symmetric Counterfactual Controls Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13006 - RePlan-VLA: Progress-Aware Replanning for Long-Horizon Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23843 - Ask the Peers: Ranking NFR Coverage Gaps for Requirements Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23296 - Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26567 - BeFit: Shifting Complexity from Weights to Bernstein Activations for Resource-Constrained Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23520 - WorkWorlds: Evaluating Agents in a Company Built Before the Task Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23806 - Embodied Graph: A Relational World Model for Long-Horizon Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24115 - ExiST: Existence-Aware Self-Training for Semi-Supervised Multi-Organ Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23581 - From Data to Valves: A Self-Learning, Production-Grade Edge Stack for Sustainable HVAC Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24052 - Recurrent Domain Incremental Adaptation of Time-Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24075 - Hierarchical Control of Antiphase Synchronization in Biomorphic Spiking Neural Architectures for Locomotor Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22639 - 3D GameDev Arena: Benchmarking Coding Agents That Plan, Build, and Playtest extreme Long-Horizon Browser Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24073 - LLM-Guided Cyber-Physical Attack Path Identification in Smart Grids Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24765 - Weight Space Programming for Vision Language Model Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23615 - Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23651 - MANGO Arena: Same Seeds, Different Chains Evaluating LLM Agents in a Disrupted Supply Chain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23613 - FusionCLIP: Multimodal Contrastive Pretraining for Fusion Plasma Diagnostics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09493 - WorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15805 - CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01802 - VideoACE: Benchmarking Agentic Video Understanding through High-Frame-Rate Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24184 - LProp: Propagating Latent Uncertainty through Evidence-Conditioned Belief Revision in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23564 - Grading Executable Legal Rules Against Independent Records: Transitional Provisions and Korean SME Status Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24055 - Does the Action Matter? Probing Action-Conditioned Semantic Forecasting as a World Model for Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24840 - Grounding Radiology Reports in 3D Chest CT: Results of the ReXGrounding Challenge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23862 - Conditional What-If Generation for Radio Access Network Energy under Rare and Unseen Contexts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24208 - Accounting for Purchased Artificial Intelligence Inference in Corporate Greenhouse Gas Inventories: A Token-Based Method Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10660 - Attention Is Not Relevance: Challenging the Causality of Attention in Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24051 - Orbits as Strong Models: Kolmogorov Structure Function under Symmetry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.40290 - KnowMe Paper Radar: Lightweight Discovery of Promising Papers in the Age of Autoresearch Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23702 - Local AI Agents in Power Electronics Simulation: Deployment, Measurements and Costs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24880 - Typed Knowledge over Constructive Institutions: A Proof-Relevant Type Theory for Verified Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15108 - SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26587 - Fuse to Recognize the Unseen: Class-Relative Infrared-Visible Fusion for Open-Vocabulary Semantic Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24316 - Kernel Ridge Attention: Nonlinear Memory with Selective Forgetting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23896 - Movie2Game-Bench: Holistic Evaluation of Film-to-Game Adaptation Beyond Playability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24669 - Neural Circuit Architectural Priors for Rat Locomotion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23364 - Toward Agentic Retrieval-Augmented Generation for Enterprise Retail Workflows over Heterogeneous Data Sources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25096 - SixthView: A Benchmark for Hidden-View Reconstruction and 3D Assembly Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23891 - Reading Human Preference from Looped Transformer Internal States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09870 - Interpreting Timestamp Permutations in Dynamic Link Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23753 - Operational Proto-Introspection in Looped Language Models: Reading Correctness Before the Answer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18553 - PhoneValue-Bench: A Dual-Ground-Truth Scorecard Benchmark for Smartphone Recommerce Inspection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00791 - Fast Bayesian Methods for Uncertainty Quantification in Sparse AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24159 - When Single Agent Is Enough: Rethinking Multi-Agent Systems for Automated Code Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23283 - RefinementGuard: Counterexample-Directed Semantic Qualification for Hidden Agent-Tool Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23611 - A Geometric Coding Theorem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13796 - TOGBench: Benchmarking and Improving Tiny-Object Generation Fidelity in Aerial Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23840 - Choosing What to Observe: Budget-Paired Counterfactual Audits for Credible Evaluation of Visual Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24867 - When Code Works but the License Doesn't: Evaluating License Constraint Handling in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23299 - LEDGE: An Efficient Simulator for Distributed LLM Serving on Heterogeneous Edge Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24085 - Robustness of Text-Only Adapted Speech LLMs for Spoken Semantic Parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21453 - Gaussian Primitive Fusion for Any-Resolution Multimodal Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24164 - Optimize the Cob, Then the Kernel: Optimizing Beam Search for Generative Recommendation Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23339 - Disentangling generalization and memorization in large language models using chess Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16823 - Language Models Make New Research Sound Old Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23546 - Openhagen Worlds: Calibrated Environments for Measuring and Training Scientific Discovery Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24711 - MillBill: A Machining Agent with Geometric Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22565 - Soft Mixture of Quantum Experts for Hybrid Quantum-Classical Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24798 - Evidence-Based Credit Assignment for Search-Augmented Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23824 - GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23476 - CounselTraj: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24168 - Toaster: Nonlinear Memory from Cascaded Linear Memories and Target Propagation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23648 - Choosing the Right Representations: Task-Aware Fusion for Multimodal Materials Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24641 - Do Frontier Model Ingredients Add Up? A Replicated Factorial Study of Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24540 - HYPER: Hypothesis-Guided Planning for Evidence-Seeking Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19008 - LLM-Assisted Multi-Fidelity Bayesian Optimization: Fusing Expert Knowledge with Numerical Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24377 - MAVE: Reconstructing Editable 3D Blockouts from Film Shots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22464 - Risk-Controlled Correction for Frozen Multimodal Models under Missing Modalities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23886 - Beyond Corpus-Driven Imitation: Evolving Musical Mindsets in the Agentic Orchestra via Quantum Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24290 - Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19782 - LAGR: Language-Aware Grasp Re-Ranking for Task Oriented Grasping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23858 - What Does a Harness Buy? Tokens, Mostly Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04433 - Who Is Behind the Harness? Verifying Model Identity in Coding Agents through Behavioral Fingerprinting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28559 - Structured Extraction of Diffraction Data from Covalent Organic Frameworks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23680 - Clover-35B-A3B-Preview Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24636 - Intent Contracts: Taking Tools Away from Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24025 - Resolution as Attention for Efficient Agent Memory Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24422 - F$^3$: What Makes Good Experience in World-Action Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24708 - MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02014 - ABSClaw: From Invented Worlds to Reality-Grounded Social Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24517 - Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15198 - PhysDial: Adapting Pretrained Video Models for PDE Simulation under Changing Physical Conditions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23498 - Learning to Decide with AI Assistance under Human-Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12646 - How Path Integral Diffusion Decides a Finite Spin Glass Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11826 - A Capability Framework for Evaluating Agentic AI Platforms in Regulated Enterprises Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24039 - ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26829 - NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24552 - Implementing Binary Transformers with Approximate Memories with Permutation Invariance Enabled Selective (PIES) Protection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23358 - AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24313 - Which Tokens, in What Order, and How Fast? A Theoretical Analysis of On-Policy Distillation Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23397 - Bias-Only Training Dynamics in ReLU Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24797 - Negotiating Control and Accountability among Stakeholders in High-Risk AI Use Cases: Development and Evaluation of the Method ALIGN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24609 - Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24512 - From Points to Trajectories: Rethinking Multimodal Alignment for Physical Events Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24249 - AGAMOTTO: An AI-Enabled Framework for Time-Critical Tactical Course-of-Action Evaluation and Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24568 - Depth Before Breadth: Reverse-to-Forward Curriculum with Advantage Decomposition for LLM Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24697 - Asking but Missing: Decision Coverage in Natural-Language Data Querying Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23864 - Practical Assessment of Agentic Systems in Acoustics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39685 - BOS Summary: The First Token Matters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23508 - Games played by Exponential Weights Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.06676 - General progress substitutes for specific training data in language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24844 - Rethinking Fixed-Horizon Latent Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24001 - Think Offline, Act in Real Time: Self-Improving Visual Game Agents through Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24590 - MEM-STRESS: Longitudinal Field Study of a Wearable-Informed AI Chatbot for Stress Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23691 - GSExplorer: Interactive World Generation with a Persistent 3DGS World State Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01543 - FlashReFocus: Interactive Image Refocusing in Seconds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23297 - Inherited Adapter Experts for Replay-Free Domain-Incremental Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24145 - Choosing Supervised Post-Processing for Frozen Person Detectors: Information, Object Changes, and Complete Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24003 - Lodestone: Automated Semantic Discovery of Datacenter Hardware Specialization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23663 - Counterfactual World Models: JEPAs That Reason About "What If" Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24778 - EVA-RSI: Recursive Self-Improvement of Video Evaluators for Judging Temporal Quality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23890 - LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02883 - JEPA as a Transferable Optimizer: Learning and Understanding Black-Box Optimization from Reward-Agnostic Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23608 - Brownian Bridge Diffusion-Assisted Joint Channel Estimation and Data Detection for Jamming-Resilient OFDM Receivers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28778 - Reducing Inference Cost of Coding Agents with Timeout Cascades Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24324 - A System 1 Decision Model for Medical Multiple-Choice Questions Built on Frozen Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23832 - Harvesting Expert-Parallel Bubbles for Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24496 - Neoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic resonance imaging with clinical variables Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26105 - Cardiac MRI-informed electrocardiography enables biologically grounded cardiomyopathy detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23925 - SEE: Unlocking the Hidden Perception of Frozen VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23962 - FairPGT: Partitioned Graph Transformers for Dual-Level Fair Graph Clustering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23631 - Reusing formal Vlasov-Maxwell proofs to certify plasma solver outputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23319 - Confidence-Based Materials Data Quality Assessment via Domain Knowledge and Graph-Structured Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23342 - Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24357 - CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14226 - LAaDT-DSS: decision support for non-experts on rooftop PV, incentive and grid simulations under Turkish tariff rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24810 - RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23855 - RiskWorld: Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18442 - CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22563 - FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19881 - Can you make models believe false facts in the prompt? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23938 - Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23908 - TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07441 - Management of Behavioral Addictions via Artificial Intelligence based Digital Technologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23341 - A Survey on Collaborative Mechanisms Between Large and Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.07460 - Learning Trajectories Leave Decodable Traces in Neural Network Weight Space and Internal Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24782 - VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15789 - How do features act in an individual prediction? Separating standalone and interaction effects with a case-based taxonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27821 - What competing constraints reveal about representation learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15995 - Glyph: An Interpretability Engine for AI-Driven Scientific Discovery from Clinical Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08922 - CoreQ: Mismatch-Corrected Successive Rounding for LLM Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05902 - ProtoBridge-CLIP: Observation-Masked Finding Prototypes for Medical Image--Report Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24002 - Panini- Feasible Grammar For Robot Designs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23567 - Auditing World-Model Explanations in Retail Forecasting: Faithfulness, Accuracy and Price Response Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20811 - H3Remover: Reinforcing Video Object Removal without Paired Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24633 - Training Language Models for Introspective Oversight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23365 - Co-Pilot for Health: Personalized Algorithmic AI Nudging to Improve Health Outcomes Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2401.10816 - REALM: Retrospective Encoder Alignment for LFP Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14867 - ReactBench-AD: Do Driving VLAs and World-Action Models React to Imminent Hazards in Their Path? Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.20011 - Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18397 - Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.19244 - AdaS-ViT: Test-Time Adaptive Routing for Spiking Vision Transformers with Ultra-High Energy Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23728 - When Does Continual Pre-Training Help? A Controlled Study of Dialectal Adaptation for Qu\'ebec French Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24699 - The Largest Tractable Subclass of Multi-Scale Allen Temporal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24498 - Check Your Blind Spots: Decision-Guided Perception by Probing the Planner with Hypothetical Objects Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23030 - Dual-Manifold Variational Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23964 - Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24877 - How Reward Gain Imbalance Shapes Ranking: Rethinking Rubric-Based Reward Aggregation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24005 - Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23639 - Auditable Clinical Support with Decision Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23700 - Extracting Training Data from Diffusion Language Models via Infilling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24173 - Learning Martial Arts Motion Skills for Animating Opponents in VR Sparring Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23825 - Study and Improvement of Search Algorithms in Stochastic Perfect-Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24486 - Evaluating invariance training with certified answer-changing controls in neural graph algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23907 - Entropy-Regularized Integrated Gradients for Stable Feature Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23600 - Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04326 - RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23410 - Beyond the Sink Token: Sink-Guided Key Editing in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23516 - Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23751 - Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24788 - How Complete Must an Environment Be to Train a Capable GUI Agent? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23946 - Vanguard: Knowing When to Trust the Draft in Speculative Vision-Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23917 - NullTok: empirical-null token selection for training-free long video understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23881 - Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17102 - Human-AI Mutualism Is Unstable under Capability Asymmetry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23322 - Markets for Compute and Inference: Structure, Financing, and Risk Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20242 - Learning through Discernment: when a small language model learns from user feedback on the job, and when it decays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23716 - Query-Driven Learning for Lifted Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34747 - MonitorVLM:A Vision Language Framework for Safety Violation Detection in Mining Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03666 - Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15500 - CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23276 - Generative AI in Software Testing: Practitioners' Perspectives on the Benefits, Challenges, Opportunities, and Risks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23256 - MoE-Context: Show the Model Only What It Needs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24379 - RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23466 - AllotNet: an Interpretable Mixture-of-Experts Choice Model for Moral Judgement in Humanitarian Aid Allocation, Validated against a Planted Synthetic Population Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23474 - SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13669 - ARISE: Practical Self-Evolving Memory for Accurate and Cost-Efficient Enterprise Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23588 - Improving Outdoor Multi-cell Fingerprinting-based Positioning via Mobile Data Augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.19405 - Measuring What Matters in the Age of AI: The Research Software Metrics Landscape Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23253 - Keeping Shielded Data-Driven Controllers Safe Under System Evolution via Model Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24428 - Where the Tokens Go: Heat, Entropy and Error in Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23375 - ReliFlow: Reliability-Calibrated Residual Transport for Combinatorial Single-Cell Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23999 - LusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.23454 - Chain-of-Thought Hidden States Reveal Task-Solving Directions for Direct Answers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24598 - Tracking Representations in LLM Reasoning Traces for Iterated Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23403 - Enhancing Active Learning Performance with Initial Data Selection Based on Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24384 - Multi-Agent Memory Inconsistency: Where Factual Conflicts Disappear in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22245 - From real to synthetic: PSG-GAN learns sleep apnea signal dynamics for AI training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24436 - Linearized 2-Simplicial Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09307 - OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24302 - EnvAgent: Multi-Agent Approach to Building Science Environments in the Clouds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23258 - MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28384 - HorizonBench: Long-Horizon Personalization with Evolving Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17283 - A Foundation Model to Measure and Predict Human Behaviour Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24830 - Mixtures of In-Context Learners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.02830 - GateWatch: Low-Overhead LLM Monitoring with Boolean Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24619 - PANC: Prior-Aware Normalized Cut for Training-Free In-Context Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06912 - Test-Time Symmetrization: Scaling Laws for Model-Agnostic Learning under Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24032 - Knowing What You Know: A Trait Theory of Reviewer Value in Human-AI Cognitive Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24932 - MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15463 - PIPETTE: Prompt Injection Purple-Teaming for Robust LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24362 - A Hybrid Exact-Heuristic Solver for the Integrated Passenger and Parcel Transportation Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22043 - When Figures Disagree with Text: Evaluating Autonomous Visual Evidence Verification in Scientific Papers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24353 - Metrics-in-the-Loop: Complexity Feedback Reshapes Agent-Written Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23817 - How Generative Models Generate: A Concise Guide to the Generative AI Landscape Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24728 - FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23601 - I2I Backdoor: Backdoor Attacks against Image-to-Image Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.10445 - Towards Reliable Scaling Laws for Tabular Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24214 - Regularizing Treatment Leakage for LLM-based Uplift Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20794 - KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24294 - Vibe-Trading: Towards Agent-Native Trading Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24845 - Replay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24059 - FormalFixer: Intent-Aligned Automated Hardware Repair via Joint Refinement of Specifications, Assertions, and RTL Implementations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24037 - Goemans's Unsplittable-Flow Conjecture: The Anatomy of AI-Assisted Counterexample Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23244 - The Digital-Energy Recomposition of the Kitchin Cycle: Exploratory Evidence from U.S. IT and Irish Data-Centre Series (1995-2025) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33122 - Anticipating or Speculating? Making Futures Pay in AI Ethics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22268 - The Obsolescence of High-Level Code: Agentic Generation from Semantic Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23249 - AgentAbstain: Do LLM Agents Know When Not to Act? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10059 - CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09127 - Language Models Can Rewrite Their Own Weights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21885 - Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24221 - The 7th International Verification of Neural Networks Competition (VNN-COMP 2026): Summary and Results Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24114 - SIGMA: speaker-isolated, symptom-structured multimodal estimation of depression severity from clinical interviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23348 - Beyond Replacement: Levenshtein Editing for Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23750 - TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15729 - KVBuffer: IO-aware Serving for Linear Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19049 - Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24651 - Evaluating Governed LLM-Driven ML Experimentation: Lifecycle, Provenance, and Failure Metrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23678 - HealthCLBench:Evaluating Context Learning in Health Conversations through Controlled Case Clusters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22362 - When Does Learning to Stop Help? Configuring Risk-Controlled Early Exit for Reasoning-Model Services Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30852 - MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07058 - How K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10780 - MARBLE: An Agentic Benchmark for Spatial Reasoning and Visual Abstraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.22992 - Risk-Calibrated Intent Routing for Conversational AI via Signed Lexical Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00262 - MINT: Meeting-time Indicators for Truncation in Multi-Step Off-Policy RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24413 - AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00515 - Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24453 - Angular Conditional Distillation: Overcoming Classifier Geometry Mismatch Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23941 - Image Watermarking With Memory Across Reissuance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23363 - Towards Pose-Robust Few-Shot Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24360 - GenPFN: An In-Context Tabular Foundation Model Approach for Augmenting Small Datasets in Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14804 - Can Weight-Space Programming Alter Learned Ethical Priorities? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24330 - AeroRSI: Recursive Self-Improvement for Aerial Vision-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24077 - Mapping the AI Supply Chain: Dependencies, Vulnerabilities, and Market Concentration in the AI Ecosystem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24927 - MLE Agents: Autonomous ML Engineering in Large-scale Recommendation Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23910 - Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04804 - SciFigQual-Bench: Scientific Figure Quality Assessment with Manuscript-Linked Context Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27084 - Horizontal Flow Matching for Single-Cell Spatiotemporal Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24764 - A Mechanistic Analysis of In-Context Learning and Out-of-Context Hallucination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24000 - Improving Cross-Lingual Token Representations by Adding a Pinch of SALT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09953 - ReflectScene:MLLM-Guided Closed-Loop Diffusion for 3D Indoor Scene Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23845 - Nothing to Declare: Steering a single neuron increases concealment in AI teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24475 - The Illusion of Relief: How GenAI Redistributes Cognitive Workload in Software Organizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23286 - Meta$^n$: Recursive Self-Improvement through Emergent Depth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24735 - Arbor: How Search Policy Shapes Agent Behavior in System Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12563 - 2D Gum-Net: Unsupervised Dense Elastic Image Registration via Symmetric Correlation and Spectral Pooling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12805 - SpiderMark: Hybrid Watermarking for Generative AI via Algorithmic Injection and Learning-Based Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24200 - Elysium: Simulation-Free Unbalanced Schr\"odinger Bridges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24763 - TOMAS: Topology-Aware Operation Modeling and Adaptive Staging for Egocentric Hand Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23970 - Rational Ensemble Logic for Cohort Discovery with Real-World Electrophysiology Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23708 - Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09154 - JUDOR: CTDE-Based Multi-Agent Reinforcement Learning for the Co-Optimization of Joint UAV Motion and Decentralized Opportunistic Routing in Delay-Tolerant Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04590 - GALA: Gallery-Level Alignment for Real-Life Vision Decoding from EEG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24206 - Communicative On-Policy Distillation: Distilling Black-Box Teacher Capabilities through Communication for Long-Horizon Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23673 - Agentic Harness Engineering Beta: Requirement-Centered Evolution of Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24924 - Reliability by Architecture: Agentic Workflows for Validated Multi-Physics Simulation from Natural Language Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23473 - Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.08231 - GRAFT: Execution-Guided Genetic Recombination for Agent Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23509 - Systematic Mapping Protocol. Generative AI-Augmented Requirements Engineering: A Systematic Mapping Study of Practices, Specifications, and Reuse in Software Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23349 - The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26651 - Probing agent overeagerness in realistic settings with continuation audits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24491 - SurgCBVR: A Multi-Domain Benchmark for Content-Based Surgical Video-to-Video Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23347 - Ephyra: A Property-Based Testing Framework for the LLM Era Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2611.23282 - Temporal Rank in Recurrent Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24394 - Idempotency Is Not Recovery: A Fault-Injection Study of Language-Model Agent Tool Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23353 - Meta-RL with Bayesian Linear Task Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20974 - A Hierarchical Onboard Vision-Language-Navigation Framework for Aerial Robots in Complex Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23930 - OracleZoom: Reference-Constrained Recursive Image Super-Resolution Beyond Ground Truth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06490 - Once Upon a Bias: Gender Stereotyping in LLM-Generated Children's Stories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24156 - Toward Out-of-Distribution Generalization in Neural AC Power Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23729 - ElephantAgent: Contextual State Continuity in Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01919 - Diagnostic Accuracy and Navigation Behavior of Vision-Language Model Agents Reading Emergency CT and MRI Examinations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23480 - FedE2E: One-Shot Federated Learning for End-to-End Autonomous Driving with Closed-Loop Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24254 - Hearsay: Who Can Audit the Record a Deployed Agent Harness Writes? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32495 - Interaction-as-a-Judge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17895 - Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06400 - DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26924 - How Well Do Generalist CT Foundation Models Differentiate Liver Tumors? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24122 - Human-AI Interactions and Societal Pitfalls Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2309.10448 - MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10592 - Mitigating fix reversal: Counterfactual constraints for function-level vulnerability detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24489 - Dependency Fabrication in Repository Deployment Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23305 - QDA: Closed-Loop LLM Quantization Design with Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23388 - Who are you? The Personal Imitation Game Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24888 - Reinforcement Learning with Reference-Based Rewards for Language Model Reasoning and Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.09895 - StatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23257 - OCTR2A: Real-Time RGB-to-BEV Trajectory Projection and Forecasting at Urban Intersections Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24352 - SCAFFOLD: Toward Warrant-Preserving Evidence Transport for Reusable LLM-Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23990 - From Data Quality to Data Trustworthiness in AI-Driven Software-Intensive Embedded Systems: A Systematic Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23252 - What Moves the Ceiling on Automated Audit: from General Code to Scientific Code, Results and Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23250 - Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11263 - WorldRuler: Interactive World Modeling under Configurable Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24869 - DuoCook: An Overcooked-Inspired Benchmark for Visual Planning and Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31511 - FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23560 - Where Is the Cost of Third-Party API Routers in Agentic Software Development? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23624 - Disagreement-Guided Agentic Data Curation for Multimodal Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14256 - The Value Semantics Layer: Enabling Machine-Understandable Databases for Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23629 - SpecLook: Speculating Where to Look for Fast and Reliable Agentic MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23483 - BiMa-ECGSR: reconstructing the 12-lead ECG from reduced lead sets with bidirectional state-space models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23345 - Generating Adversarial Events: A Motion-Aware Point Cloud Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08230 - Counterfactual Feature Regularization for Expansion-Based Class-Incremental Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09145 - HydroMind: A Checkable Agent for Autonomous Hydrological Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23323 - Cost-Efficient LLM Evaluation: A Framework for Narrow Confidence Intervals Under Fixed Budgets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29140 - Receiver-Conditioned Clarification for Multi-Agent Food Assistance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23572 - Response-Relevant Information Is Not Sufficient for Neural Training-State Equivalence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23245 - Modeling LLM Reasoning Dynamics with Structural Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23749 - Repository-Grounded Rubrics for Execution-Free Evaluation of Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23309 - Benchmarking LLM abilities on postdoc-level natural science problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24321 - CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28792 - When Does Reallocating a Sampling Budget Pay? Instance-wise Allocation for Neural Routing Solvers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27917 - MECI: Multi-Element Collaborative Interaction for Multimodal Entity Linking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24522 - Risk-Triggered Search: Behavior-Preserving Safe Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24409 - APS: Adaptive Partitioning-Based Frame Selection for Long Video Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24079 - Continual Tool-Space Extension Learning for Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23810 - Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18366 - GA-VINO: A Geometry-Aware Variational Physics-informed Neural Operator for Mindlin-Reissner Plates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16624 - Reliability is a user-specific property of large language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23732 - BaseRSI: Recursive Self-Improvement of a Base Vision-Language Model via Training-Free Harness Internalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24578 - automodel: A Skill for Agentic Model Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24347 - Hypnos: A Dual-Phase End-to-End Platform for Scalable Continual Learning at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24637 - Space-X: Self-Evolving Spatial Agents Weaving Clues into Evidence Chains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24004 - Worth Another Look:Constrained World-Model Planning for Visual Inspection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24187 - CaDO: Formal Verification-Guided Multi-Agent Framework for Causal Dataset Repair and Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24406 - Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10138 - Auditing Path-Specific Fairness Across Causal Discovery Algorithms: A Heart Failure Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15926 - HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23398 - What Survives the Shift from Text to Pixels? Conditional Protection against Prompt Injection in Image-Rendered Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.24231 - Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01209 - MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.01935 - Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22432 - PEARL: Personalized Streaming Video Understanding with Runtime-Defined Concepts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20422 - CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02527 - VeriMath: Human-in-the-Loop Generation and Verification of Curriculum-Aligned Mathematics Assessment Items Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.23456 - Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22897