TILens Daily Edition 2026-09-03 Filters: topic=ai, github=hidden Stats: 591 articles, 7 sources, 586 research papers Top topics: AI, AI Research, Information Retrieval ## News - I built 47 client-side developer & AI tools because I'm tired of bloated, ad-heavy utility sites Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/jarvissing/i-built-47-client-side-developer-ai-tools-because-im-tired-of-bloated-ad-heavy-utility-sites-3bj9 - AI Skill of the Day Digest — August 2026 (Part 2) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/ai-skill-of-the-day-digest-august-2026-part-2/ - Everything That Happened in AI Today (Wednesday, September 2, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-september-2-2026/ - OpenAI Builds Shutdown Controls as AI Agents Gain More Power Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-automated-ai-shutdown-controls/ ## Research - A Storage-Retrieval Gap in Parametric Knowledge Graph Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25489 - Explainable Information Processing in Particle Swarm Optimization through Landscape and Search Behavior Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06272 - Sample Complexity of Linear Quadratic Regulator Without Initial Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14210 - Gradient Prediction with Control Variates in the Cheap-Forward Regime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.05187 - Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02790 - A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02107 - UE5M3 FP4 Block Scaling for Stable Language Model Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02846 - Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01675 - Toward Explainable and Policy-Aware AI for Carbon Credit Price Prediction: A Research Framework for Emerging Carbon Markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01765 - oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02672 - Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21377 - What Drives Success in Physical Planning with Joint-Embedding Predictive World Models? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24497 - From Digital to Physical Reservoir Computing: Co-Optimizing Soft Robotic Reservoirs via Dynamics Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00484 - SpecXMaster Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23101 - TransfHAR: Self-Supervised Wrist Representations for On-Demand Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15861 - Untangling the Mechanisms of Misleading Context in Medical Question Answering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02754 - Bandits in Prod: Hyperparameter Optimization at Inference Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01335 - XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02083 - Rethinking Learnability in Offline Data-driven Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01493 - A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08371 - Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02519 - Enhancing brain age estimation with structural MRI and synthesized cerebral blood volume maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.01865 - Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02451 - Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01962 - Shortcomings and capacities of real-constrained neural networks in complex spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04390 - A Power Law in Logarithm's Clothing: On the Scalability of Graph-Based Vector Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02143 - RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02497 - Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22667 - Humanoid Safe Stop via Learned Stoppability Value Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02358 - The Dynamics of Continuous Mixture Collapse in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02049 - Beyond State Consistency: Behavior Consistency in Text-Based World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13824 - Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02649 - Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02155 - Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02404 - Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01999 - Dimension Dependent Correlation Gap Bounds under Restricted Independence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02659 - The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Shared Category Geometry in Small Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16741 - Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02417 - Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21960 - DiDrive: A Risk-Aware Hierarchical Diffusion Framework for Safe Offline Reinforcement Learning in Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01609 - CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02774 - What Is Worth Representing? Representational Empowerment for Continual Model Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02322 - Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02548 - Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02237 - RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01729 - DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02170 - Similarity-Aware Personalized Federated Learning in Heterogeneous Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02241 - Enabling KV Caching of Shared Prefix for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07571 - Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.01617 - Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17117 - Context Inference Attacks Without Jailbreaks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01663 - Cantelli Constrained Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22993 - RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01622 - CAHR-Net: Condition-Adaptive Hysteresis Reconstruction for Compact and Interpretable Magnetic Core Loss Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01991 - CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01673 - Cliff: Learning Process Rewards from the First Mistake Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02817 - Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01997 - Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01768 - Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18364 - A Common Measure of Communication for Speech Brain-Computer Interfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02887 - Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.00966 - Schr\"odinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02196 - EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00566 - GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.06315 - Constrained Group Relative Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05863 - Do Large Language Models Capture the Diversity in their Training Data? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02275 - Diagonal Multi-omics Integration of Heterogeneous Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16968 - QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00224 - Source Distribution Estimation by Posterior Averaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02622 - Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02111 - Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01736 - AI Contextual Measurement for Recovering Individual and Group-Level Effects: Validation Against Survey Measures and an Occupational Application Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02821 - SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02140 - Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.05033 - General Demographic Pre-trained Models for Enhancing Predictive Performance Across Diseases and Population Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.07330 - Towards Solving the Gilbert-Pollak Conjecture via Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22365 - Network-Aware Forecasting on Wireless Access Points Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01957 - MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16077 - A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02538 - Double-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clusterin Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.18143 - Windowed thinning and query complexity for the bouncy particle and Zigzag samplers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28413 - CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02265 - Eliciting ESG Preferences for Reinforcement Learning-Based Portfolio Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02677 - CAT-Flow: Curvature-Adaptive sTeps for Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01746 - SPADE: SPaT Attack Detection from the Connected Vehicle's Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02741 - A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01679 - TC-Next: Zero-Shot Multimodal Cyclone Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02085 - TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22975 - When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03096 - Reinforcement Learning and Rule-Based Peer-to-Peer Pricing in Residential PV-BES Communities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01680 - Multi-Agent Retrieval-Augmented Generation for Efficient Cloud Knowledge Base Search in Telecom SNOC Environment Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.01618 - FlashKAN: B-Spline KANs via Truncated Power Form Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01956 - Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02373 - Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02728 - A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07724 - Learning-Based Reconstruction Attacks on Coordinate-Obfuscated Point Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02568 - Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01647 - DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07678 - TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02540 - Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01567 - Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.12018 - Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01839 - Bayes-Optimal BER and AUC: Estimation and Evaluation of Estimators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02304 - PRISM: An Agentic Multi-Model Architecture for Proactive Safety in Autonomous Transportation Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01623 - Stream-CQSA: Exact Out-of-Memory Recovery for Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20819 - OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29829 - The Implications of Linguistic Illegibility for LLM Security Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02852 - Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05605 - Doubly Stochastic Adaptive Neighbors Clustering via the Marcus Mapping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.02932 - OutageDiT: A Generative Foundation Model for Power Outage Forecasting and Scenario Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01896 - Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29531 - H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02684 - Improved Gradient Descent Lower Bounds Beyond Nesterov Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02855 - A Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps: Scaling a MEDLINE Atlas to 1.05 Million Neurons on a Single Consumer GPU Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24067 - Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02126 - From topology learning to graph generation: A unifying perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02286 - Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01072 - When Literature Data Mislead Artificial Intelligence in Materials Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01621 - CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02450 - Compositional Spectral Prompts for LLM-based Online Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02093 - No Data Wasted: A Semi-supervised Generative Model for Incomplete Multi-view Data Integration with Missing Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11180 - Objective-Behavior Alignment: Diagnostics for MORL Policy Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21321 - Private Computation Space: Experience with Trusted Multi-Cluster Federated Learning for Agriculture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01667 - CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01925 - How Far Do Simple Transformations Translate Across Text Embedding Models? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05980 - Generative Diffusion Surrogates with Analytical Variance Schedule Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01705 - Tri-Band Channel Measurement-Enabled Multi-Layer Digital Twin for Terahertz Wireless Data Centers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01699 - Rethinking the Teacher-Student Framework for Test-Time Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02507 - Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02623 - Quantum MeanFlow: single-shot generative sampling on NISQ hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02186 - Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25095 - The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28980 - From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02771 - Learning the Constitutive Behavior of Materials via Neural Operators and Causal Attention: Case Studies in Plasticity and Damage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02194 - From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02198 - Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16337 - Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oracle Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01689 - Adaptive Graph-of-Islands Evolution for Automatic Feature Engineering with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23286 - Nova: An End-to-End MLIR Compiler for Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00029 - On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01947 - Held-out evidence resolves follow-up measurement decisions in biological screens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27651 - ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18579 - Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06257 - LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02246 - DLM-One: Diffusion Language Models for One-Step Sequence Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.00290 - TaRA: Training-Aware Low-Rank Adaptation Initialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02639 - Marginal Expected Revenue for Jointly Ranking Auction and Fixed-Price Listings in E-Commerce Sponsored Search Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.01628 - RCProb: Probabilistic rule extraction from classification tree ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25304 - Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01786 - Post-Training Language Models for Gold-Medal Performance in Coding Competitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02849 - Variation Spaces for Encoder--Decoder Neural Operators: Approximation and Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01244 - AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02339 - Quantum Speedups for Sampling and Non-convex Optimization with Stochastic Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.03626 - hLLM: Single Pass Decoding for Generative Reranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01807 - MISApp: Multi-Hop Intent-Aware Session Graph Learning for Next App Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21653 - Interpretable Symptom Vectors for Depression in a Large Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01832 - Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30081 - FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20574 - Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25184 - GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02162 - Multi-Mask Diffusion Language Models for Few-Step Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19686 - Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08146 - Dutch Books for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02797 - When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02438 - Action abstractions for amortized sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.15184 - Hardware-Accelerated Instance Segmentation for Resource-Constrained Space Robotics with Criticality Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02219 - A Computational Comparison of Fourier Spectral Differentiation and Spatial Automatic Differentiation in Periodic Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02110 - MM++: Post-Hoc Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17352 - Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01091 - FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01683 - Entangled Representations Amplify Collateral Damage in Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02285 - Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01633 - Poisoning Attacks on the PGM-index Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02328 - Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02766 - Simulating Classification Models for Ex-Ante Evaluation of Predict-Then-Optimize Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02191 - Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01914 - FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01691 - Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.02042 - Language Models Can Control Their Own Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02737 - Prompting the Unknown: Understanding Response Uncertainty in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.14845 - Discriminative World Models for Web Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02885 - Towards One-for-All Robustness Across a Continuum of Threat Levels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02440 - Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02264 - Three Necessary Principles for Self-Supervised Visual Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08309 - Learning Spectral-Like Mesh-Free Discretisations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02833 - ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02549 - Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26841 - GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12275 - One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19128 - Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02172 - Learning and extrapolating scale-invariant processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14810 - Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00528 - 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 - Latent unified smooth Hamiltonians for excited state chemistry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01871 - Learning Encodings by Maximizing State Distinguishability: Variational Quantum Error Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11552 - DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02468 - Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2309.06349 - The Axiomatic Trader: Latent Regularity, Information Budgets, and the Canonical Form of a Quantitative Investment System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23416 - Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01945 - Morphology signal in whole slide image foundation models can automatically triage slides Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01987 - SocialBuddy: Tailoring Search Agent for Social Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01641 - SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02293 - LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02734 - Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02652 - VoiceLongMemEval: Do Assistants Remember How You Sounded? Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.00570 - HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02138 - Inference-Native Zeroth-Order Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28760 - AdaBoosting Text Prompts for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00684 - Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22642 - Deep Reinforcement Learning for Reach-Avoid-Stay Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.02898 - Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01936 - Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02566 - A Study of Conditional Diffusion Models for Open-Loop Control under Dry Friction and Stiction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01756 - Achieving More with Less: A Tensor-Optimization-Powered Ensemble Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.02936 - Adversarial Stress Testing of Outlier Detection in Subjective Image Quality Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06554 - Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01952 - Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04147 - Training seeds and model-selection stability in recommender-system evaluation Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.02499 - Emotional regulation improves deep learning-based image classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13081 - WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02177 - Scaling an Autoregressive Transformer for Single-Cell Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02961 - Optimal Transport for Network Comparison: A Review with Machine Learning Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27500 - Neural operators approximate strongly continuous convex monotone semigroups Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02727 - OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01933 - Freeze, Diffuse, Decode: Task-Aware Adaptation of Transformer Embeddings for Antimicrobial Peptide Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.23120 - RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02250 - Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02510 - GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02160 - Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02302 - Refining Heuristic-Based Bitcoin Address Clustering with Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01942 - Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01615 - Nonasymptotic CLT and Error Bounds for Linear Two-Time-Scale Stochastic Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.09884 - Neural Variational Cut Posteriors without Upstream Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10268 - Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09791 - SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02203 - WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01608 - D-FROST: Decentralized Federated pRompt-tuning via Optimal tranSporT for Non-IID and Imbalanced Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01802 - ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21969 - Feature Interaction Modeling for Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28762 - Monotonic anomaly detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23158 - IDEEA: training-free Input-Dependent stEEring via Activation cluster matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02089 - Deep denoising autoencoder-based non-invasive blood flow detection for arteriovenous fistula Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2306.06865 - A Unified Particle Filter LSTM for Data-Driven Process Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01967 - GMTRouter: Personalized LLM Router over Multi-turn User Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08590 - Federated LoRA Adaptation of BiomedCLIP Across Four International Chest X-Ray Cohorts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02101 - Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02638 - Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01723 - Modular Expert Merging for Biomedical Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04731 - Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02018 - Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01676 - On the Expressive Power and Limitations of Multi-Layer SSMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14501 - Robust Streaming PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1902.03223 - Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02006 - DynaTokens: Controlling Token Dynamics for Continual Video-Language Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06662 - Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24814 - Secure AI-Driven Super-Resolution for Real-Time Mixed Reality Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15823 - Online Non-Monotone DR-Submodular Maximization Matching the Offline $0.401$ Factor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02145 - SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2606.29894 - Clustering Three-Way Data with Outliers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.05288 - Perceptually Regularized Diffusion Model for Image Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02016 - Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01492 - Training nGPT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01284 - SEBA: Sample-Efficient Black-Box Attacks on Visual Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.09681 - IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02422 - DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02059 - A computational approach to maximum likelihood thresholds for colored Gaussian graphical models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02382 - DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02068 - On Cost-Aware Designs for Sequential Hypothesis Testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.19067 - Reinforcement learning to choose optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01811 - Probing Cultural Signals in Large Language Models through Author Profiling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16749 - Prototype-guided transfer of sparse literature knowledge for electrolyte additive discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02209 - Differentiable Electricity-Market Clearing for Gradient-Based Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02646 - HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02746 - Graph Machine: Towards Better Pretraining via Edges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02881 - Connections between the F\"ollmer process and the denoising diffusion probabilistic model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18040 - WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07710 - Pooling and Drift in Delayed Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01761 - GRADSOLVE: fast exact gradients for ODE ensembles on GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02876 - MESSY STREETS: A Benchmark for Geocoding Real-World Addresses Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01612 - KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01780 - Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02316 - CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.20845 - MERGED: Multimodal Entity Resolution via Generated Expert Reasoning Distillation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01913 - MELON: A Large-Scale Dataset for Multi-Event Text-to-Long-Video Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01654 - GRAND-HC: Graph-Refined Author Name Disambiguation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01636 - Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02011 - Genuine Information Needs of Social Scientists Looking for Data Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02303 - Recommender System as Slow and Fast Thinkers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02671 - MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusion Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01619 - Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.08389 - SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02062 - ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01865 - Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01846 - Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01616 - Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02745 - Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01610 - GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric Matching Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02012 - Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01642 - Index-Free Dynamic Edge Retrieval with Energy-Tail-Aware Partial Scans Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01820 - Beyond Context Windows: Persistent Discovery Context for Data-Centric Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02129 - The Vocabulary Gap Is an Equity Gap: Register Mismatch in Retrieval Systems for Public-Benefits Access Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01645 - Adaptive Test-Time Inference for Text2Cypher with Trace Budgeting and Selective Refinement Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02324 - Beyond Modality Harmony: Orthogonal Purification and Topology-Guided MoE for Conflict-Aware Multimodal Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02152 - NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01657 - ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.29652 - The Utility of LLMs in Recommender Systems Explanation Evaluation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01627 - MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02379 - Graph Neural Team Recommendation: An Integrated Approach Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01631 - Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.04547 - Skim and Skip: Hierarchical Adaptive Inference for Efficient Multimodal Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01613 - Not All Matches Are Equally Valuable: An Online Experiment of Retention-Focused Recommendation in a Job-Matching Platform Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01652 - Group-Aware Adaptive Retrieval for Evidence Navigation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02188 - From Feature Interaction to Feature Transport - A Unified Block for Scalable Recommendation Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01655 - 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 - Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.00618 - Multimodal Language Models as Text-to-Image Model Evaluators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.00759 - MASkills: Continual Skills Optimization for Multi-Agent LLM Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02094 - MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09435 - UTP-Bench: Uncertainty-aware Travel Planning Benchmark Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02421 - Thinking effort aligns between humans and reasoning models in abductive reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01867 - When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28346 - Predictors of Loneliness in Older Adults Using Multimodal Analysis of Speech and Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02606 - Knowledge Editing for Masked Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03924 - EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02133 - AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21144 - Exploring Collaboration between a language and a non-language agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00474 - PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23092 - TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03072 - Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01794 - What Transfers Under Source Shift? Definitions, Examples, and Fine-Tuning for Climate Disclosure Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17952 - DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02796 - The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01852 - GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15602 - Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16991 - Mediocrity is the key for LLM as a Judge Anchor Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16848 - Are Non-English Papers Reviewed Fairly? Language-of-Study Bias in NLP Peer Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07119 - Privacy Washing: Detecting Internal Contradictions in Privacy Policies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02055 - SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29270 - CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02273 - From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02262 - Evaluating the Evaluator: Summarization Metrics and LLM-Judges beyond English Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.17039 - What's in a Name? Morphological Shortcuts by LLMs in Pharmacology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05616 - AI agents reshape consensus formation in human groups Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02122 - From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02679 - NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02366 - When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15276 - ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12983 - LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10103 - Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00588 - 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 - Door-in-the-Face Requests and Refusal Behaviour in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02707 - APEx: Distillation of Agent Procedural Experience for Adaptive Deep Research Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02253 - DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02685 - Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01687 - Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02396 - BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27380 - SHARD: Safe and Helpful Alignment via Self-Reframing Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15517 - CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12639 - Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22453 - Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27309 - Using Large Language Models for Legal Decision-Making in Austrian Value-Added Tax Law: A Comparative Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.08468 - Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02749 - Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17372 - How Do Prompt Variations Affect Energy Consumption in On-Device LLMs? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01798 - Do Large Language Models Always Tell The Same Stories? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17350 - HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21815 - CogEvol: Towards Efficient and Reliable Learning Environment Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30968 - Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22396 - Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18216 - EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17698 - SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01737 - Do Cantonese-Adapted Language Models Better Predict Cantonese Reading? A Cross-Model Eye-Tracking Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02163 - GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30188 - AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01828 - Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01918 - Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02309 - LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06973 - A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26236 - Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02091 - 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 - HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02056 - Elite political incivility is rising across democracies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22411 - Direct Construction of Disambiguated Knowledge Bases from Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03729 - EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02783 - Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01671 - NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01971 - Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24661 - MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01772 - The Enforcement and Feasibility of Hate Speech Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12289 - OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02158 - SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26550 - PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02480 - CALIBURN: Self-Calibrated LLM Unlearning Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02824 - SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02292 - Lot Machine: Multimodal Lot Extraction from Auction Catalogs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30510 - text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02115 - VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01788 - SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00030 - TUX: Measuring Human--AI Tacit Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30930 - Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02473 - PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02272 - On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29496 - CARPAS: Towards Content-Aware Refinement of Provided Aspects for Summarization in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07177 - Can Coding Agents Reproduce Findings in Computational Materials Science? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00803 - PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01708 - A Survey of Transformer-based Language Models with Focus on Efficiency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.16893 - DiffIE: Diffusion-based Open Information Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02315 - When Persona Attributes Improve Population Alignment in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02526 - Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18593 - ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02780 - Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.21907 - GAPS: Dimension-Level Gates for Conditional Activation Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01878 - LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19800 - Candidate Generation and Definition-Guided Verification for Sentence-Level Depression Symptom Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01833 - C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.02131 - Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29920 - PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01658 - Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.10136 - EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01611 - Accurate in space, unreliable in time: how LLMs represent national cultural change Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01902 - Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22230 - Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16310 - SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02343 - Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02414 - When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Logic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01741 - TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01810 - Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2602.03619 - GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06992 - Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02255 - How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02482 - FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19539 - VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20728 - CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26293 - HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02772 - Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16847 - SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23713 - Automated Researchers Can Mitigate Well-characterized Alignment Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28945 - LeakageBench: Document-Level Leakage Risk for Redacting Personally Identifiable Information in Document Images Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02207 - Reviewing the Reviewer: LLM-Assisted Reviewer Feedback Generation for Guideline Compliance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10118 - REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10963 - Translating Classical Poetry into Modern Prose Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02806 - WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02651 - How Output Format Confounds Data Quality and Capability in Instruction Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02015 - Debias-SparseGPT: Bias-Aware Pruning for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02496 - User Feedback Provides a Unique Signal that LLMs Can not Detect Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02859 - The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03043 - Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12062 - CORAL: An LLM-Native Harness for Production Recommender Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02730 - Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02108 - Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21617 - Choosing a PEFT Variant for Per-Patient Dysarthric ASR: A Single-Speaker Case Study on Two ASR Bases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02735 - Whose Judgments Count? Representation Gaps in Crowdsourced Content Moderation Produce Unequal Protection from Perceived Toxicity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01625 - SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02336 - FinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01198 - A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02054 - A Layered Taxonomy for Chinese Learner Grammatical Error Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02153 - Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01659 - Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30022 - PolERo: Studying Political Evasion in Romanian Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02391 - Expos\'ia: Teaching and Assessment of Academic Writing Skills for Research Project Proposals and Peer Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06536 - Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02702 - Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02116 - ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02215 - Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24026 - SKILL.state: Scalable Long-Horizon Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26263 - CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02459 - OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23722 - Open-World Semantic Segmentation with Sensitivity Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08308 - FemWear: A Parameter-Efficient Wearable Foundation Model for Women's Health Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08244 - Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30485 - The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07671 - AI Mathematician: Towards Fully Automated Frontier Mathematical Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22451 - Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02805 - RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02282 - SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15550 - Rating the Raters: Rasch Measurement Theory for LLM Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27463 - HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01730 - InsightSeg: Reusing Correction Insights for Guideline-Consistent Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02002 - Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04562 - Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02399 - Inference-Time Optimization of Prompt Embeddings in Diffusion Models: A Comparison of sep-CMA-ES and Adam Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03913 - RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02731 - 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 - Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02268 - How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01660 - BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28026 - SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02786 - Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02861 - SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02217 - Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01685 - MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25457 - MeanField Surrogate Modeling for Scalable Runtime Scheduling of Concurrent Heterogeneous AI Inference on Shared GPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02109 - CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20129 - Induction and Inquiry via Probabilistic Reasoning over Language and Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01815 - Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02371 - PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30378 - A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29705 - From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03557 - Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01749 - Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Oversight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01976 - Stepwise Think-Critique: Interleaved Reasoning and Self-Critique in a Single LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15662 - Benchmarking Language Models for Statistical Problem Formulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01982 - SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25202 - ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07328 - When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01814 - Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01834 - Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02057 - Fair Stable Matching: A Nash Social Welfare Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02354 - Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02046 - RAPIDMap: Rapid Multi-Agent Pipeline for Interpretable Disaster Mapping from Satellite and Street-view Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00046 - Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01861 - The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01909 - CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02074 - LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24780 - Agent Memory Is a Surface for Endogenous Authorization Laundering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01836 - Collective creativity in hybrid societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02620 - Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29291 - PIE-APT: Abductive Planning over Temporal Dynamic Knowledge Graphs via Incremental Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27287 - Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02191 - PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02231 - SAUF-Net: Structure--Appearance Representation Learning with Uncertainty Feedback for Semi-Supervised Medical Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02247 - FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27284 - Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12406 - Bernini: Latent Semantic Planning for Video Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22344 - Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07468 - Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02028 - Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21052 - FlatLands: Generative Floormap Completion From a Single Egocentric View Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16016 - Can escalation channels redirect reward hacking toward defect disclosure? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29460 - TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06349 - ORB-SVM : An Innovative Hybrid Framework for Efficient Brain Tumor Detection from MRI Scans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02333 - Automated Vulnerability Injection in Smart Contracts Using Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02624 - Fetch.ai: An Architecture for Modern Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.18699 - FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19828 - Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02502 - Dictionary-Guided Mutation Operators for Automated HDL Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01775 - Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02750 - frb100-40 After Two Decades: An Optimality Certificate and a Preregistered Search Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02804 - OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00015 - An Energy-Based Mechanism for Compositional Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04745 - SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01849 - Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01924 - Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01408 - Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02760 - Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00575 - InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02004 - PEARL: Path-Entity Aligned Relational Learning with Contextual Subgraphs for Inductive Knowledge Graph Completion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02216 - Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01168 - Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02242 - Auditory Illusion Benchmark for Large Audio Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02277 - HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02029 - Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01693 - Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02092 - Competitive Market Behavior of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02580 - Zeta-Lite: A Concurrent, Branchable In-Browser SQL Database for Agentic Memory Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2609.01818 - Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01873 - Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17499 - Addressing Trust in AI Systems through Education: A Didactic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02453 - ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02067 - Why we need an AI-resilient society- Profiling Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/1912.08786 - ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01992 - Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10534 - FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02168 - Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01662 - Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08552 - Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02224 - UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11557 - READY or Not: Reliable Enterprise Agent Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02095 - Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02529 - InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02233 - When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27984 - Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02244 - 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 - 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 - When Agents Implement Systems: A Case Study in Defects, Detection, and Evaluation Rigor Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01985 - PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02236 - Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01779 - Git4Data: Database-Native Version Control for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02106 - DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion and Action Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02252 - CHASE: Cache-Hole-Adapted Skip Exit for Looped State-Space Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10110 - Subcellularly Resolved Single-Cell Embedding Learning with Transcriptomic data, Protein Structure and Localization Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02344 - Unifying biomedical knowledge in a modern multimodal graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27269 - 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 - A Data-Driven Multimodal Method for Early Detection of Coordinated Abnormal Behaviors in Live-Streaming Platforms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01649 - CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02270 - MineTRACE: An Evidence-Grounded Interactive Reasoning System for Mineral Prospectivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02060 ## Community - US gov sides with OpenAI on issue of training LLMs on copyrighted material Source: hacker-news Topic: General (+AI) URL: https://techcrunch.com/2026/09/02/u-s-government-sides-with-openai-on-issue-of-training-llms-on-copyrighted-material/