| 1 | GRADSOLVE: fast exact gradients for ODE ensembles on GPUs | ⌥ repo | cs.MS | 2026-09-02 |
| 2 | MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse Fusion | ⌥ repo | cs.CV | 2026-09-02 |
| 3 | Benchmarking RAW and RGB Restoration in Image Signal Processors | ⌥ repo | cs.CV | 2026-09-02 |
| #4 | SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment | ⌥ repo | cs.AI | 2026-09-02 |
| #5 | EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction | ⌥ repo | cs.CL | 2026-09-02 |
| #6 | ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding | ⌥ repo | cs.CV | 2026-09-02 |
| #7 | Video-Based Palm-Vein Authentication under Challenging Conditions | ⌥ repo | cs.CV | 2026-09-02 |
| #8 | Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems | ⌥ repo | cs.AI | 2026-09-02 |
| #9 | SPADE: SPaT Attack Detection from the Connected Vehicle's Perspective | ⌥ repo | cs.CR | 2026-09-02 |
| #10 | LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates | ⌥ repo | cs.LG | 2026-09-02 |
| #11 | RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models | ⌥ repo | cs.CV | 2026-09-02 |
| #12 | H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression | ⌥ repo | cs.LG | 2026-09-02 |
| #13 | Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis | ⌥ repo | cs.CV | 2026-09-02 |
| #14 | WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities | ⌥ repo | cs.CL | 2026-09-02 |
| #15 | Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face) | ⌥ repo | cs.CV | 2026-09-02 |
| #16 | From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images | ⌥ repo | cs.CV | 2026-09-02 |
| #17 | Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations | ⌥ repo | cs.CV | 2026-09-02 |
| #18 | MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval? | ⌥ repo | cs.CV | 2026-09-02 |
| #19 | ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction | ⌥ repo | cs.LG | 2026-09-02 |
| #20 | Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs | ⌥ repo | cs.LG | 2026-09-02 |
| #21 | Rethinking the Teacher-Student Framework for Test-Time Adaptation | ⌥ repo | cs.LG | 2026-09-02 |
| #22 | Debias-SparseGPT: Bias-Aware Pruning for Large Language Models | ⌥ repo | cs.CL | 2026-09-02 |
| #23 | CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI | ⌥ repo | cs.AI | 2026-09-02 |
| #24 | MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts | ⌥ repo | cs.CL | 2026-09-02 |
| #25 | LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory | ⌥ repo | cs.CV | 2026-09-02 |
| #26 | Structured-Prior-Guided Diffusion Inpainting with Physical Consistency for Traffic Sign Augmentation | ⌥ repo | cs.CV | 2026-09-02 |
| #27 | Poisoning Attacks on the PGM-index | ⌥ repo | cs.DB | 2026-09-02 |
| #28 | YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification | ⌥ repo | cs.CV | 2026-09-02 |
| #29 | Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds | ⌥ repo | cs.AI | 2026-09-02 |
| #30 | If It Moves, Radar Knows: A Physics-Aware Radar Transformer for Class-Agnostic Moving-Object Detection | ⌥ repo | cs.CV | 2026-09-02 |
| #31 | Auditory Illusion Benchmark for Large Audio Language Models | ⌥ repo | cs.SD | 2026-09-02 |
| #32 | Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging | ⌥ repo | cs.CV | 2026-09-02 |
| #33 | FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection | ⌥ repo | cs.CV | 2026-09-02 |
| #34 | TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval | ⌥ repo | cs.CV | 2026-09-02 |
| #35 | Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation | ⌥ repo | stat.ML | 2026-09-02 |
| #36 | CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting | ⌥ repo | cs.CV | 2026-09-02 |
| #37 | WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading | ⌥ repo | cs.CR | 2026-09-02 |
| #38 | Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models | ⌥ repo | cs.LG | 2026-09-02 |
| #39 | EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision | ⌥ repo | cs.AI | 2026-09-02 |
| #40 | Semantic Signal-Assisted Inspection and Recovery Allocation in Reverse Logistics | ⌥ repo | cs.AI | 2026-09-02 |
| #41 | Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models | ⌥ repo | cs.CL | 2026-09-02 |
| #42 | Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics | ⌥ repo | cs.CV | 2026-09-02 |
| #43 | MASkills: Continual Skills Optimization for Multi-Agent LLM Systems | ⌥ repo | cs.AI | 2026-09-02 |
| #44 | Compositional Spectral Prompts for LLM-based Online Time Series Forecasting | ⌥ repo | cs.LG | 2026-09-02 |
| #45 | Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models | ⌥ repo | cs.MM | 2026-09-02 |
| #46 | CHIME: Credit-Aware Hierarchical Memory Evolution for Long-Horizon Agentic Planning | ⌥ repo | cs.AI | 2026-09-02 |
| #47 | DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting | ⌥ repo | cs.LG | 2026-09-02 |
| #48 | InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation | ⌥ repo | cs.CV | 2026-09-02 |
| #49 | Benchmarking Language Models for Statistical Problem Formulation | ⌥ repo | cs.AI | 2026-09-02 |
| #50 | Refining Heuristic-Based Bitcoin Address Clustering with Graph Neural Networks | ⌥ repo | cs.LG | 2026-09-01 |
| #51 | Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens | ⌥ repo | cs.CL | 2026-09-01 |
| #52 | Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence | ⌥ repo | cs.AI | 2026-09-01 |
| #53 | Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge | ⌥ repo | cs.LG | 2026-09-01 |
| #54 | DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation | ⌥ repo | cs.CV | 2026-09-01 |
| #55 | Allocate Before You Embed: Adaptive Visual Input Allocation for Video Embeddings | ⌥ repo | cs.CV | 2026-09-01 |
| #56 | Toward Explainable and Policy-Aware AI for Carbon Credit Price Prediction: A Research Framework for Emerging Carbon Markets | ⌥ repo | cs.LG | 2026-09-01 |
| #57 | SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition | ⌥ repo | cs.CL | 2026-09-01 |
| #58 | From Visual Cues to Spoken Narration: Rethinking Audio Description | ⌥ repo | cs.CV | 2026-09-01 |
| #59 | Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation | ⌥ repo | cs.CL | 2026-09-01 |
| #60 | Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation | ⌥ repo | cs.SE | 2026-09-01 |
| #61 | Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation | ⌥ repo | cs.SE | 2026-09-01 |
| #62 | CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? | ⌥ repo | cs.CL | 2026-09-01 |
| #63 | StudentSim: Training LLM-based Student Simulators | ⌥ repo | cs.CL | 2026-09-01 |
| #64 | A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios | ⌥ repo | cs.CV | 2026-09-01 |
| #65 | Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks | ⌥ repo | cs.LG | 2026-09-01 |
| #66 | Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories | ⌥ repo | cs.LG | 2026-09-01 |
| #67 | Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall | ⌥ repo | cs.CL | 2026-09-01 |
| #68 | Sierpiński--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation | ⌥ repo | cs.CG | 2026-09-01 |
| #69 | DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting | ⌥ repo | cs.CV | 2026-09-01 |
| #70 | Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation | ⌥ repo | cs.CV | 2026-09-01 |
| #71 | LatentPress: Context Compression Beyond Text and Vision | ⌥ repo | cs.LG | 2026-09-01 |
| #72 | Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study | ⌥ repo | cs.CR | 2026-09-01 |
| #73 | GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions | ⌥ repo | cs.CL | 2026-09-01 |
| #74 | Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement | ⌥ repo | cs.AI | 2026-09-01 |
| #75 | Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers | ⌥ repo | cs.AI | 2026-09-01 |
| #76 | Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds | ⌥ repo | cs.RO | 2026-09-01 |
| #77 | Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications | ⌥ repo | cs.CV | 2026-09-01 |
| #78 | CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection | ⌥ repo | cs.LG | 2026-09-01 |
| #79 | MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition | ⌥ repo | cs.CV | 2026-09-01 |
| #80 | Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations | ⌥ repo | cs.AI | 2026-09-01 |
| #81 | InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations | ⌥ repo | cs.CL | 2026-09-01 |
| #82 | Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA | ⌥ repo | cs.CL | 2026-09-01 |
| #83 | PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction | ⌥ repo | q-bio.GN | 2026-09-01 |
| #84 | Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR | ⌥ repo | cs.CL | 2026-09-01 |
| #85 | ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence | ⌥ repo | cs.CV | 2026-09-01 |
| #86 | LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting | ⌥ repo | cs.AI | 2026-09-01 |
| #87 | Bandits in Prod: Hyperparameter Optimization at Inference Time | ⌥ repo | cs.LG | 2026-09-01 |
| #88 | Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment | ⌥ repo | cs.CL | 2026-09-01 |
| #89 | A Composable Evaluation System for Reproducible Omni-Modal Foundation Model Evaluation | ⌥ repo | cs.AI | 2026-09-01 |
| #90 | GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation | ⌥ repo | eess.IV | 2026-09-01 |
| #91 | Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems | ⌥ repo | cs.AI | 2026-09-01 |
| #92 | FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers | ⌥ repo | cs.CV | 2026-09-01 |
| #93 | Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents | ⌥ repo | cs.LG | 2026-09-01 |
| #94 | MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence | ⌥ repo | cs.CR | 2026-09-01 |
| #95 | S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models | ⌥ repo | cs.CV | 2026-09-01 |
| #96 | H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning | ⌥ repo | cs.AI | 2026-09-01 |
| #97 | CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs | ⌥ repo | cs.LG | 2026-09-01 |
| #98 | Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement | ⌥ repo | cs.CV | 2026-09-01 |
| #99 | On the Design Fundamentals of Pixel Text Representation Learning | ⌥ repo | cs.CV | 2026-09-01 |
| #100 | Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning | ⌥ repo | cs.CV | 2026-09-01 |
| #101 | When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting | ⌥ repo | cs.LG | 2026-09-01 |
| #102 | P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement | ⌥ repo | cs.CV | 2026-09-01 |
| #103 | Modelpedia: A Catalog of Model Findings for the Meta-Science of AI | ⌥ repo | cs.LG | 2026-09-01 |
| #104 | Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration | ⌥ repo | cs.LG | 2026-09-01 |
| #105 | Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models | ⌥ repo | cs.SD | 2026-09-01 |
| #106 | PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition | ⌥ repo | cs.CL | 2026-09-01 |
| #107 | SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models | ⌥ repo | cs.CV | 2026-09-01 |
| #108 | ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation | ⌥ repo | cs.CV | 2026-09-01 |
| #109 | PredErase: Training-Free Object-and-Effect Removal with Predictive Latent Guidance | ⌥ repo | cs.CV | 2026-09-01 |
| #110 | CERF: Communication-Efficient and Retraining-Free Collaborative Perception | ⌥ repo | cs.CV | 2026-09-01 |
| #111 | Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling | ⌥ repo | cs.CL | 2026-09-01 |
| #112 | DualStake: Dual-Path Confidence Calibration in Deep Research Agents | ⌥ repo | cs.CL | 2026-09-01 |
| #113 | On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios | ⌥ repo | cs.CV | 2026-09-01 |
| #114 | RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation | ⌥ repo | cs.AI | 2026-09-01 |
| #115 | Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control | ⌥ repo | cs.LG | 2026-09-01 |
| #116 | ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection | ⌥ repo | cs.CV | 2026-09-01 |
| #117 | FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation | ⌥ repo | cs.AI | 2026-09-01 |
| #118 | AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation | ⌥ repo | cs.AI | 2026-09-01 |
| #119 | One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning | ⌥ repo | cs.AI | 2026-09-01 |
| #120 | Advanced Pixel Diffusion Model with Guided Sparse Global Refinement | ⌥ repo | cs.CV | 2026-09-01 |
| #121 | StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? | ⌥ repo | cs.AI | 2026-09-01 |
| #122 | Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures | ⌥ repo | cs.LG | 2026-09-01 |
| #123 | Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning | ⌥ repo | cs.CL | 2026-09-01 |
| #124 | Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis | ⌥ repo | cs.LG | 2026-09-01 |
| #125 | Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection | ⌥ repo | cs.CV | 2026-09-01 |
| #126 | Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs | ⌥ repo | cs.AI | 2026-09-01 |
| #127 | ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything | ⌥ repo | cs.AI | 2026-09-01 |
| #128 | Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports | ⌥ repo | cs.CR | 2026-09-01 |
| #129 | Differentially Private Paired Table-Image Multimodal Synthesis | ⌥ repo | cs.CR | 2026-09-01 |
| #130 | SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation | ⌥ repo | cs.CL | 2026-09-01 |
| #131 | DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection | ⌥ repo | cs.CV | 2026-09-01 |
| #132 | DK-GBMKKM: Dynamic Kernel-Space Granular-Ball Multiple Kernel $k$-Means Clustering | ⌥ repo | cs.LG | 2026-09-01 |
| #133 | TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data | ⌥ repo | cs.SD | 2026-09-01 |
| #134 | Beyond Landmark Extraction: A Framework for Robust Geometric Feature Construction in Structured Image Classification | ⌥ repo | cs.CV | 2026-09-01 |
| #135 | BrainDiff: Longitudinal Report Generation for Multimodal Brain MRI | ⌥ repo | cs.CV | 2026-09-01 |
| #136 | Real-Time Neuromorphic Spectrum Intelligence Simulator | ⌥ repo | eess.SP | 2026-09-01 |
| #137 | Predicting Program Exit Code with LLMs and Programming Language Semantics | ⌥ repo | cs.PL | 2026-09-01 |
| #138 | Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs | ⌥ repo | cs.AI | 2026-09-01 |
| #139 | EM^2Mem: Event-Centric Multimodal Memory for Large Language Models | ⌥ repo | cs.CL | 2026-09-01 |
| #140 | Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers | ⌥ repo | cs.SE | 2026-09-01 |
| #141 | ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation | ⌥ repo | cs.AI | 2026-09-01 |
| #142 | Validity-Aware Jailbreak Evaluation for Large Language Models | ⌥ repo | cs.AI | 2026-08-31 |
| #143 | Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models | ⌥ repo | cs.CL | 2026-08-31 |
| #144 | Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective | ⌥ repo | cs.CR | 2026-08-31 |
| #145 | Towards a Belief-Based World Model for LLM Agents | ⌥ repo | cs.AI | 2026-08-31 |
| #146 | mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers | ⌥ repo | cs.AI | 2026-08-31 |
| #147 | Physiological Information Reliability: Cross-Layer Adaptive Resource Allocation for Cardiovascular Sensing | ⌥ repo | eess.SP | 2026-08-31 |
| #148 | SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling | ⌥ repo | cs.CV | 2026-08-31 |
| #149 | Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration | ⌥ repo | cs.RO | 2026-08-31 |
| #150 | RestoreBench: Can AI Agents Restore Power Flow Convergence? | ⌥ repo | cs.AI | 2026-08-31 |
| #151 | Dr. Claw: An AI Scientist Workspace for Vibe Research | ⌥ repo | cs.AI | 2026-08-31 |
| #152 | Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models | ⌥ repo | cs.AI | 2026-08-31 |
| #153 | Latent Mechanisms of Language Control in Multilingual Language Models | ⌥ repo | cs.CL | 2026-08-31 |
| #154 | Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries | ⌥ repo | cs.CY | 2026-08-31 |
| #155 | Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts | ⌥ repo | cs.CL | 2026-08-31 |
| #156 | NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings | ⌥ repo | cs.CL | 2026-08-31 |
| #157 | CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for Driving Affordance Prediction | ⌥ repo | cs.CV | 2026-08-31 |
| #158 | Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems | ⌥ repo | cs.AI | 2026-08-31 |
| #159 | Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning | ⌥ repo | cs.CV | 2026-08-31 |
| #160 | Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM | ⌥ repo | cs.CV | 2026-08-31 |
| #161 | QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization | ⌥ repo | cs.LG | 2026-08-31 |
| #162 | Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning | ⌥ repo | cs.CL | 2026-08-31 |
| #163 | Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving | ⌥ repo | cs.CV | 2026-08-31 |
| #164 | WHALE: A Simple Recipe for Joint Harness-Weight Optimization | ⌥ repo | cs.LG | 2026-08-31 |
| #165 | Recursive Criticality of AI Self-Improvement | ⌥ repo | cs.AI | 2026-08-31 |
| #166 | Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving | ⌥ repo | cs.CV | 2026-08-31 |
| #167 | PaperGym: Rubric-Centered Evolution for Research-Plan Generation | ⌥ repo | cs.CL | 2026-08-31 |
| #168 | Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions | ⌥ repo | cs.LG | 2026-08-31 |
| #169 | VeriCam: A Verification Baseline for the Classification of Unknown Data | ⌥ repo | cs.CV | 2026-08-31 |
| #170 | BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing | ⌥ repo | cs.AI | 2026-08-31 |
| #171 | Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents | ⌥ repo | cs.CL | 2026-08-31 |
| #172 | Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence | ⌥ repo | cs.AI | 2026-08-31 |
| #173 | LISynSeg: Data-Centric Label-to-Image Synthesis for Cross-Modality Whole-Heart Segmentation | ⌥ repo | cs.CV | 2026-08-31 |
| #174 | Identity-Conditioned Latent Consistency Distillation for Face Synthesis | ⌥ repo | cs.CV | 2026-08-31 |
| #175 | Driving on Memory | ⌥ repo | cs.CV | 2026-08-31 |
| #176 | One note in three: a verified census of three deployed AI scribes, and the instrument that counted it | ⌥ repo | cs.CL | 2026-08-31 |
| #177 | LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It | ⌥ repo | cs.CL | 2026-08-31 |
| #178 | TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification | ⌥ repo | cs.LG | 2026-08-31 |
| #179 | Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation | ⌥ repo | cs.LG | 2026-08-31 |
| #180 | CogEvol: Towards Efficient and Reliable Learning Environment Generation | ⌥ repo | cs.CL | 2026-08-31 |
| #181 | Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding | ⌥ repo | cs.LG | 2026-08-31 |
| #182 | Annotated Surrogate Retrieval for Polish Statutory Law | ⌥ repo | cs.CL | 2026-08-31 |
| #183 | Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space | ⌥ repo | cs.LG | 2026-08-31 |
| #184 | Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation | ⌥ repo | cs.CL | 2026-08-31 |
| #185 | PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation | ⌥ repo | cs.CL | 2026-08-31 |
| #186 | VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement | ⌥ repo | cs.CV | 2026-08-31 |
| #187 | GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures | ⌥ repo | cs.RO | 2026-08-31 |
| #188 | Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V | ⌥ repo | cs.CV | 2026-08-31 |
| #189 | Whole-Body MRI Classification via Prompt-Based Clinical Conditioning | ⌥ repo | cs.CV | 2026-08-31 |
| #190 | A Composition-Aware Pretraining Framework for Geospatial Foundation Models | ⌥ repo | cs.CV | 2026-08-31 |
| #191 | E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation | ⌥ repo | cs.LG | 2026-08-31 |
| #192 | Tracing distinguishability through transformer processing with stochastic LayerNorm | ⌥ repo | cs.LG | 2026-08-31 |
| #193 | TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos | ⌥ repo | cs.CV | 2026-08-31 |
| #194 | Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions | ⌥ repo | cs.CV | 2026-08-31 |
| #195 | CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation | ⌥ repo | cs.CV | 2026-08-31 |
| #196 | Learning Materials Properties from Scarce Labels and Unlabeled Crystals | ⌥ repo | cs.LG | 2026-08-31 |
| #197 | OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding | ⌥ repo | cs.CL | 2026-08-31 |
| #198 | CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy | ⌥ repo | cs.LG | 2026-08-31 |
| #199 | HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving | ⌥ repo | cs.AI | 2026-08-31 |
| #200 | InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning | ⌥ repo | cs.CV | 2026-08-31 |