TILens Daily Edition 2026-09-04 Filters: topic=ai-research, github=hidden Stats: 576 articles, 5 sources, 575 research papers Top topics: AI, AI Research, Information Retrieval ## News - GPT-6 Astra: Everything You Need to Know About OpenAI’s New Model Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/gpt-6-astra-everything-you-need-to-know-about-openais-new-model/ ## Research - A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann Vehicle Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04147 - Identification of Bivariate Causal Directionality Based on Anticipated Asymmetric Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26024 - Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19491 - BASP: Communication-Efficient Batch-Aware Sequence Parallelism for LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03151 - EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03522 - FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03241 - Evaluating Graph Neural Networks for Change-Criticality Classification in Maritime Navigation Charts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02996 - ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10226 - Subspace Inference Enables Efficient Active Reward Learning from Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04066 - Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03142 - Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04165 - RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03937 - Robust PAC Learning of Concurrent Stochastic Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04189 - RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04007 - RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03956 - Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14991 - Learnable composition for neural operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03069 - Learning to Concatenate Quantum Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14931 - Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04011 - ObserverBench: Testing Mechanistic Estimates for Intervention and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03026 - FedPS: Federated Preprocessing for structured data via aggregated Statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10870 - KernelFoundry: Hardware-aware evolutionary GPU kernel optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12440 - Temperature Scaling Attack Disrupting Model Confidence in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06638 - MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01734 - KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03166 - Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03343 - Active learning for data-driven reduced models of parametric differential systems with Bayesian operator inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00038 - Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03941 - LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03528 - Physics-Informed Neural Network Surrogate for Oxygen Vacancy Dynamics in epitaxial $\mathrm{SrTiO_3}$ on Si memristors via Dynamic Spectral Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02966 - Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12462 - RCProb: Probabilistic rule extraction from classification tree ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25304 - Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03190 - Reliable Selection of Heterogeneous Treatment Effect Estimators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18464 - Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03480 - RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03379 - Observation-Aligned Two-Stage Domain Decomposition for Physics-Informed Traffic State Estimation with Sparse Fixed Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08028 - Residual neural networks overcome the curse of dimensionality for semilinear heat equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03626 - MidSurfNet: Learning Face Pairing for Mid-surface Abstraction of Thin-walled CAD Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01891 - A Peer-Relative Representation Learning Framework for Energy Inefficiency Identification in Mobile Network Sites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03809 - Towards a Statistical Understanding of Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03501 - Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03878 - LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18388 - ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03355 - VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03949 - SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00095 - Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.10421 - Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01431 - Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09067 - Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03442 - Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31413 - Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03762 - Mind the Gap: Robustness Risks in PII Detection Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03464 - Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04028 - Grassmann--Pl\"ucker Parametrization of Convolutional Filter Subspaces: Regularity and Closed Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03361 - Correlated initialization of deep residual networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03589 - JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25593 - A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15144 - Democratic ICAI: Debating Our Way to Steering Principles from Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28294 - Simplify to Amplify: Achieving Information-Theoretic Bounds with Fewer Steps in Spectral Community Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17104 - InKAN: B-Spline KANs via Truncated Power Form Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01956 - Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03342 - Distilling deep optical flow stereo methods to retrieve dense three-dimensional wind fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03100 - Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03036 - Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26648 - SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10734 - Introducing SINFONIA: Symplectic, slimplectic and Magnusian (Neural) Flows for Orbital Numerical Integration and Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03329 - Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05271 - Hard-ReLU Gradient Descent Selects an Event-Free Sensitivity Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30960 - Causal Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03003 - Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02998 - Mixed Data Clustering Survey and Challenges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03070 - Semantic Bayesian World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03834 - DE-Venus: A Data-Efficient RLVR Framework for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03324 - Non-Stationary Functional Bilevel Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15363 - Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15154 - Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27370 - Selective Hypergraph Refinement for Frozen Graph Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03265 - Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03851 - From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03801 - FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04021 - Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03306 - Sparse auto-regressive modeling for scene generation from multi-view images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03931 - The Head Complexity of Boolean Functions in Single-Layer Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04046 - Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03416 - BharatGather: A Culturally-Informed Benchmark Dataset for Misinformation and Fake News Detection in Indian Public Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02895 - Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02986 - Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08955 - FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15116 - Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03308 - ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19332 - Learning to Transfer Across Modes: Towards Unified Urban Mobility Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28273 - SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02963 - Constant regret in general games via higher-order optimism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04113 - When Chain-of-Thought Fails, the Solution Hides in the Hidden States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23351 - A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03457 - DrainSinkhorn: Safe Elimination for Batched Entropic Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24741 - A Real-Calibrated Synthetic-First Data Engine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09699 - Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03977 - Adaptive Resolving Methods for Markov Decision Processes with Function Approximations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12037 - Portable Causal Fairness Across Synthetic Data Generator Families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03180 - Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08216 - Witnesses Explain Anomalies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03826 - Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03900 - The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02959 - Beyond Blur: A Semantic Tri-view Pipeline for Teledermatology Gradability via Skin Micro-relief Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03095 - CRAW: Codec Robust Audio Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03107 - Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03677 - Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03504 - Conditioning Degenerate Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04090 - MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03201 - Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03981 - A Multidimensional Data-Driven Hybrid Transformer Framework for Non-invasive Continuous Blood Pressure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23276 - Towards Scaling Reinforcement Learning to Massive Populations: Learning Mean-Field Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02928 - Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03844 - Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03443 - Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04199 - Anisotropic View Distance Metric for High-Dimensional Data: Theory, Geometry, and Fast Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2206.05215 - SimCast-S2S: A Computationally Efficient Diffusion Model for Subseasonal Precipitation Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26594 - Learning-Based Collaborative MEC for LLM Inference with Soft-Deadline Awareness via Transformer-Enhanced PPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02031 - Federated Causal Discovery via Regression-Directed Cumulants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03705 - From Leakage to Fidelity: Reliable Benchmarking for Temporal Cascade Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25348 - Free Pause Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03807 - Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08665 - Generative Nested Sampling of Atomistic Thermodynamic Landscapes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03193 - Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03422 - Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02967 - DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22007 - Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00218 - Unifying Conformal Language Tasks with In-Context Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03005 - WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09447 - Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01721 - Multi-step Proximal Policy Improvement in Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03842 - Explicit Interaction Architectures for Dynamical Learning: A Controlled Study of Structural Inductive Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19101 - On the Interaction Between Model Compression and Test-Time Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03604 - LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03507 - Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12271 - RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03149 - LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03079 - Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03046 - Structured Inference with Large Language Gibbs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19264 - From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02984 - PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24207 - Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07596 - AgentRM: Enhancing Agent Generalization with Reward Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.18407 - Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29032 - Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03352 - Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09038 - An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03505 - Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03565 - Tail-Likelihood Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02987 - You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03035 - A Nesterov-Accelerated Byzantine-Robust Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02657 - Hadronic Mono-Z Dark Matter Sensitivity with Flow Matching on CMS Open Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02923 - Routing Is Not Enough: Diagnosing Intra-Adapter Subspace Contention in MoE+LoRA Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03150 - It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03436 - IDSPACE: A Novel Document Generator for Reliable Evaluation of Digital Identity Verification Systems [Extended Technical Report] Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03052 - LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03594 - MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00696 - Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03667 - SurgeGen: A Hybrid Generative Diffusion Framework for Storm Surge Scenario Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03382 - SWIM: Student Writing Simulation via Proficiency-Conditioned Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03215 - Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31184 - Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07597 - Improving precipitation forecasts in an AI weather model using observational data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03210 - Linearized subspace refinement framework to expose hidden accuracy in trained neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13989 - Parameterized Hardness of Zonotope Containment and Neural Network Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22849 - Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03533 - Improved Gradient Descent Lower Bounds Beyond Nesterov Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02855 - TRACE: Spatiotemporal Contact Memory Graph Network Simulator for Granular Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02991 - LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02931 - LatentPress: Context Compression Beyond Text and Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01507 - Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03177 - What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04726 - From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24167 - Genetic Algorithms for Tractable Bayesian Network Fusion via Pre-Fusion Edge Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03724 - Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.03901 - Latent Energy Action Planning with World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03294 - A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.06494 - Hardware-Aware FP4 FlashAttention-4 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04105 - Resolution-Aware Experimental Design under Partial Identifiability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03686 - WELD: The First Naturalistic Long-Period Small-Team Workplace Emotion Dataset for Ubiquitous Affective Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15221 - A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27341 - Spectral characteristics of autoencoder parameters as a vector representation of data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03495 - What is Smoothness? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03246 - Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03358 - Feasible but Not Safe: Constraint Violations and Report-Channel Attacks in Learned Cell-Free ISAC Association Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03147 - Relative Prime Factorization and Finite-State Presentations under Fixed Finite-Monoid Observation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03643 - Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03064 - Artificial Intelligence for Energy Optimization in Data Centers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03716 - Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02947 - When Vision Meets Graphs: A Survey on Graph Reasoning and Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03816 - DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04094 - Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25390 - AIP: A Graph Representation for Learning and Governing Agent Skills Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04781 - Evaluating GNNs for Success Prediction in Artist Collaboration Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02920 - AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15884 - Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03158 - Computing stable configurations of confined smectic liquid crystals with a deep variational framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03389 - Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02965 - Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04194 - Landmark-Based Discrimination of Injury-Associated Athlete-Sessions from Minute-Resolution Multimodal Football Monitoring Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03790 - Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04198 - OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03770 - Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09967 - Data-efficient Kernel Methods for Learning Hamiltonian Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.17154 - Language-encoded network topology enables large language models to reason about complex networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03229 - Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02969 - Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02971 - Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12500 - FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02948 - Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00669 - Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04108 - Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24851 - Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03780 - Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21696 - F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06717 - RW-TTT: Batched Serving for Request-Owned Test-Time Training State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28053 - Physics-Guided Robotic Radiation Source Localization along Arbitrary Measurement Paths in Unstructured Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27624 - From Zero to Hero: An Open LLM Ecosystem for Armenian Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03350 - OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03972 - No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02993 - Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03376 - WeatherNext 3: Increasing resolution and performance of global weather models with raw observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03582 - LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.03313 - Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04134 - Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15565 - LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04013 - Data Driven Equation Discovery for Phase-Ordering Dynamics : From Allen Cahn to the Ising Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20404 - TraveL: Transformer-based Multi-view Path Distributional Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03427 - Unlocking Lossless Speedups in LLMs via Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04010 - Beyond .WAV: Design and Software Verification of VocalCap, a Traceable Browser-Based Audio Capture System for Vocal Biomarker Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03320 - A Mathematical Theory of Reusable Neural Bases for Network Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01550 - Occupancy-based Quantile Risk Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03104 - The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03231 - Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03420 - The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03090 - SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03377 - Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20591 - Modelpedia: A Catalog of Model Findings for the Meta-Science of AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01090 - Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability Floor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03221 - Scaling Laws, Tabular Data and Actuarial Ratemaking Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03106 - Grammar-Aligned Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.21047 - B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven Methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03239 - GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08343 - Deep networks learn to parse uniform-depth context-free languages from local statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06065 - Semiparametric Inference for Counterfactual Regression under Intervention-Driven Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.02694 - Position: Unlabeled IS NOT Equal to No Human Supervision in Visual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03077 - VoxReason: Listener-Free Evaluation of Source-Grounded Speech Planning Before Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03203 - A Large Open Multi-Energy Corpus of Soil Compaction Tests, with Machine-Learning Baselines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03337 - A location-invariant estimator of extremal quantile treatment effects for heavy-tailed distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04018 - Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.09454 - Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23129 - Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03117 - What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03254 - Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04168 - Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03603 - ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18338 - Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02988 - High-Dimensional Learning Dynamics of Attention-Indexed Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03858 - HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29843 - The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25868 - Extracting Forgotten Prompts from Targeted Unlearned Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03662 - Spectral Convergence of Random Feature Method in Multiple Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03401 - From Nowcasting to Forecasting: Adapting a Reanalysis-Trained Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03763 - TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03383 - Equation Recast for Canonical Operator Learning Across Parametric PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02982 - TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07451 - Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03660 - EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03846 - A Closed-Form Formula for Consistent Lipschitz Regression on Metric Spaces with Sparse Neural Network Realizations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03129 - Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03955 - HypRQ-VAE: Hyperbolic Item Indexing for Long-Tail-Aware Generative Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03369 - Is Position Bias in Dense Retrievers Built In-or Learned from Data? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.26578 - Unified Pitch Graphs for Diagnosing Pitching Strategy Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03810 - CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04083 - ExplainRoute: A Pre-Deployment Audit Framework for Non-Answer-Giving Programming Tutors Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03470 - R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02894 - TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2408.09199 - Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02944 - The WebKurator.de Platform: Combined Regional and Topical Web Curation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03971 - Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03450 - SelfDR: Self-Distillation from Reasoning for LLM-Based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03313 - ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02486 - LLM4AIGQ: LLM-based AI Guidance Query Generation Framework for Multi Interest Mining Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03674 - From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03482 - The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04047 - RuleMem: Active Rule Memory for Long-Term Conversational Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03915 - Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2601.07978 - SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03047 - Route Based Map Matching via a Structured Codebook and Token Sequence Decoding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.22543 - PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.20047 - Multi-Task Deep Recommender Systems: A Survey Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2302.03525 - When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03454 - SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03338 - UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03290 - CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02913 - DoPR: Reusable Compressed Document Prefixes for Efficient LLM Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03311 - GRASP: Graph-Retrieval Automated Scoring Pipeline for Label-Free Multi-Topic Essay Grading Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03857 - Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03654 - Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2509.14435 - A Spectral Phase Admissibility Certificate for Complex Linear Maps Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02911 - Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07106 - Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04048 - KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land Records Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03597 - Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03953 - Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02940 - When Models Edit Too Much: On the Fidelity of Minimal Code Edits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04061 - Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03181 - TabScope: Question-Adaptive Scope Selection for Table Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03395 - Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04148 - SV-Detect: AI-generated Text Detection with Steering Vectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07313 - Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02897 - The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25510 - Typological Feature Prediction with Large Language Models: An In-Context Learning Approach Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03775 - Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02837 - Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16583 - ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04197 - Rethinking On-Policy Distillation of Large Language Models II: One Training Example Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04172 - ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10581 - HOMURA: Taming the Sand-Glass for Time-Constrained LLM Translation via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10187 - IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.15736 - Imagination Helps Visual Reasoning, But Not Yet in Latent Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22766 - Transfiver: Human-AI Co-Inference through a Shared Editable State Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03797 - Counterexamples as Feedback for Agent Self-Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02892 - Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04180 - FiMI Banking: A Sovereign Model for Indian Retail Banking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03960 - LDC: Learning to Generate Research Idea with Dynamic Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.14626 - SGD-KV: Summarization Guided KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03235 - EDIT: Evidence-Diagnosed Intervention Training for Rule-Faithful LLM Grading Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06350 - Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03936 - Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.02890 - Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03321 - Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02889 - SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02941 - Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement Behaviour Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03330 - Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10720 - Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02082 - Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03619 - User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.20721 - Opening mind by opening architecture: analysis strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03719 - Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02914 - Argument Collapse: LLMs Flatten Long-Form Public Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01736 - The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03652 - Probe Generalization as Subspace Selection for OOD Deception Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02893 - Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04736 - Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20058 - IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03781 - MIRA: A Bilingual Benchmark for Medical Information Response Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28025 - Human Psychometric Questionnaires Mischaracterize LLM Behavior Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10078 - Detecting Conversational Mental Manipulation with Intent-Aware Prompting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.08414 - Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03366 - EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26785 - Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03432 - DisclosureBeta: A Measurement-Channel Theory for Regime-Conditioned Betas from LLM-Read Risk Disclosures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02900 - Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03923 - To What Extent Do Large Language Models Understand Bangla Idioms? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03410 - RL-ADA: A World-Feedback Framework for Adversarially Robust Enterprise Dialogue Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02902 - Skill-Conditioned Gated Self-Distillation for LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28791 - Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03814 - Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00607 - RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03773 - Gaokerena: A Small Persian Medical Language Model Family Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00932 - One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02881 - Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16718 - Instruction Duplication as an Inference-Time Control Primitive Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04024 - A Reverse Sign Language Dictionary: Open-Vocabulary Sign Recognition from Continuous Signing via Video Captioning and Description Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03788 - Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03511 - Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02899 - Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03430 - Evaluating Large Language Models on Urdu Idioms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17460 - SFAD: Speculative Factuality-Aware Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00796 - What Do CAE Simulation Agents Really Need Beyond a Generic Harness? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03718 - LLMs Learn Better In-Context from Rules than from Examples Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03213 - Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03734 - SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28179 - Distilled Rapid Embedding Transfer (DRET): Parameter-Efficient Biomedical Domain Adaptation via Priority-Based Embedding Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02898 - PalmClaw: A Native On-Device Agent Framework for Mobile Phones Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13027 - Benchmarking Machine Translation on Chinese Social Media Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22931 - The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03218 - Learning to Zoom Efficiently with a Contrastive Curriculum Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03206 - PiPMRE: A Pipeline Based on Language Model for Medical Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02896 - Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03273 - A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03687 - Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02901 - Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20954 - Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03820 - Editable Visual Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04034 - Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03887 - Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00065 - Representational alignment yields generalizable safety in language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04022 - PACE: Towards Surfacing Hidden Conflicts in User Requests Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03293 - Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03502 - LexIssue: Benchmarking Legal Issue Identification in Chinese Civil Litigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02954 - Last Translation Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04173 - Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02942 - HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03580 - Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03394 - How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08348 - Relational Linearity is a Predictor of Hallucinations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11429 - Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03749 - FrameBench:A Language Understanding Benchmark Based on Frame Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03370 - Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22511 - TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22793 - Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03992 - MedQA-MM: Shortcuts Behind Medical Visual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03261 - IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03985 - Chehre: An Emoji-Prompted Dataset to Explore Perceptual Flexibility in Video Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21657 - Investigating the Ability of Large Language Models to Analyze Recipes for Diabetes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03967 - CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05520 - Pattern Over-Generalization of Knowledge Graph Embedding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03487 - How Far Can Synthetic Data Take Thai OCR? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03595 - Beyond Accuracy: Community Perspectives on Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09655 - Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03930 - Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31002 - How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03322 - K-Bench: measuring model performance on real scientific agent requests Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21601 - KnowVis: Knowledge-Centric Visual Summarization for Video Lectures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03742 - Lngram v2: Latent N-Gram Memory with Interpretable Discrete Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03426 - CROCODIL: Cross-Model Code Editing with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03894 - Large Language Models in Resolving Contextual Knowledge Conflicts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03148 - FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03331 - More Criticism Does Not Make a Better Review: EquiReview-R Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03943 - When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03467 - CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02372 - Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30912 - No country for old linguists: LLM-brain alignment underdetermines neural computation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03160 - Doesn't Stop Reasoning: Analysis of Spurious CoT Termination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03633 - VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03811 - ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05553 - Faithful by Construction: Claim-Anchored Attribution for Multi-Document Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23989 - Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30076 - Language, Language Models, and What We're Talking About Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03577 - EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25175 - Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04183 - A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04170 - VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19956 - Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03663 - CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17125 - FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03889 - StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11851 - Spurious Advantage Hidden in GRPO Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04063 - Evolving Excellence: Automated Optimization of LLM-based Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09108 - Test-time adaptation for speech enhancement with an autoregressive speech prior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03622 - CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01658 - DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03423 - PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10029 - GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03868 - Causal Probing for Internal Visual Representations in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05593 - PeroMAS: A Multi-agent System of Perovskite Material Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13312 - Beyond Reproducibility: Towards Security-Aware Evaluation of Research Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06508 - SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16276 - Measuring Harmfulness of Computer-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00935 - Dalek: A Constructive Agent Machine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03546 - TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03534 - Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27141 - A Unifying Perspective on Causal World Models: From Observations to Representations to Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13456 - Symmetries and Causality: Causal Effect Identification Beyond IID Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03697 - PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05915 - MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14202 - Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03800 - STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.03874 - Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03407 - Interface-Induced Trajectory Censoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03966 - NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13473 - GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03553 - StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03414 - Traceable TTS: Toward Watermark-Free TTS with Strong Traceability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03887 - PAWBench: How Far Are We from Probabilistically Aligned World Modeling? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27345 - Lose the Order, Keep the Hierarchy: Deordering HTN Plans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03912 - Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04096 - SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.03806 - Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09341 - InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04014 - Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03520 - A computable representation of the physical laboratory enables verifiable workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03621 - EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03629 - Inferring Affective Consciousness in an Artificial Agent: A Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03883 - Anonymization, Not Elimination: Utility-Preserved Speech Anonymization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17000 - Speculative Macro Commit for Faster Tool-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03236 - Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03493 - Environment Evolution for Terminal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04128 - From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04166 - Rethinking World Models for Safety-Critical Embodied Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03774 - A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04086 - DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03787 - Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03391 - CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03526 - Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03721 - X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17544 - Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03938 - BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03497 - Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03438 - Identifying AI Web Scrapers Using Canary Tokens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13706 - What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03515 - Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03727 - AutoGraphForge: Towards Automated Graph Theory Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03478 - Short-Window Sliding Learning for Real-Time Violence Detection via LLM-based Auto-Labeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.10866 - SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04159 - Counterfactual Routing Using Integer Programming with Constraint Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03707 - From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03590 - PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02958 - EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02739 - LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05031 - When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02964 - RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19030 - VoRTeC: Taming Foundation Flow for One-step Real time Video Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02291 - Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02990 - OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02149 - WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03554 - Efficient Test-Time Adaptation through Human-AI Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04141 - GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12821 - Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.15038 - LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18261 - TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04071 - KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03588 - Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03340 - SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03753 - Analysis of Prompt Engineering for Drug Toxicity Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03635 - A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03884 - PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03503 - Sionna RT: Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.21719 - The Attention Triangle in Audio-Video Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03586 - Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03702 - Structure and Implementation of New Practical English Textbooks Driven by Artificial Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02981 - Counterfactual Contrastive Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19032 - Catalogue Photography as a Cold Start: Toward Deployable Carbide Burr Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03995 - The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04009 - ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03620 - Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03973 - The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03425 - Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28553 - CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03818 - The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11842 - Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03483 - Xiaomi-TabLDM: A Tabular Foundation Model Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03880 - Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01207 - MasterControl Seventeen Every Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03209 - NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03527 - Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03535 - One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04190 - LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03796 - Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03860 - Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03940 - The Dually Flat Geometry of Planning as Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04005 - VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24302 - Deja Vu in Plots: Leveraging Cross-Session Evidence with Retrieval-Augmented LLMs for Live Streaming Risk Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16027 - Bioinfoysis Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03871 - ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.01865 - Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency Penalty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03460 - The Natural Language Interaction Protocol and Standard for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04135 - Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02993 - A Computationally Feasible Framework for Causal Probabilistic Explanation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04177 - LightEMMA: A Longitudinal Evaluation of Vision-Language Models for Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00284 - AI Agents Push Humans Out of the Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23642 - A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03402 - Complete Identification of Deep ReLU Networks through {\L}ukasiewicz Logic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00266 - Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is Unavailable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04127 - The impact of phase information for few-shot fine-grained image classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03829 - The Psychological Costs of Artificial Intelligence Adoption in Software Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03456 - Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04098 - Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03189 - GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03892 - GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03494 - IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04030 - Data Market Design through Deep Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.20096 - FailBench: How Reliable are VLMs at Judging Robot Task Success? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03611 - SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04167 - LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05460 - PatchBench: Evaluating AI Agents for Vulnerability Patching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04075 - Discovering High Level Patterns from Simulation Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10009 - Value-Preserving Architectures for Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03920 - ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03756 - Towards a Foundational Ontology for Identifying and Resolving Contradictions in Dialogue-based Human-Robot Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02364 - From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28974