{"total":114,"rows":[{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2603.12252","title":"EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2603.12529","title":"TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning","created":"2026-03-13","cited_by_count":6,"area":"lr"},{"id":"2603.13768","title":"Causal Tracing of Audio-Text Fusion in Large Audio Language Models","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2609.04565","title":"Extremely Sparse Supervision Incentivizes Reasoning Ability","created":"2026-09-03","cited_by_count":5,"area":"lr"},{"id":"2603.15809","title":"Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks","created":"2026-03-16","cited_by_count":4,"area":"agents"},{"id":"2605.02910","title":"CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2605.04970","title":"Skill Neologisms: Towards Skill-based Continual Learning","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2601.22530","title":"Enhancing Table Reasoning with Deterministic Table-State Rewards","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2603.19993","title":"MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI","created":"2026-03-20","cited_by_count":3,"area":"mllm"},{"id":"2604.25578","title":"Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling","created":"2026-04-28","cited_by_count":3,"area":"moe"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2605.08888","title":"DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2605.18882","title":"To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2601.21000","title":"UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.13832","title":"Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind","created":"2026-02-14","cited_by_count":2,"area":"agents"},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2602.19517","title":"Classroom Final Exam: An Instructor-Tested Reasoning Benchmark","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.19539","title":"FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment","created":"2026-03-20","cited_by_count":2,"area":"lr"},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.03869","title":"On Adaptivity in Zeroth-Order Optimization","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.27904","title":"Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.01091","title":"Deep Research as Rubric for Reinforcement Learning","created":"2026-05-31","cited_by_count":2,"area":"agents"},{"id":"2606.05988","title":"Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2607.04525","title":"Language Models Represent and Transform Concepts with Shared Geometry","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2609.04290","title":"Evidence Integration in Large Language Models","created":"2026-09-03","cited_by_count":2,"area":"rag"},{"id":"2601.21600","title":"CORE: Collaborative Reasoning via Cross Teaching","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.04604","title":"Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.15332","title":"Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2602.23088","title":"Cytoarchitecture in Words: Weakly Supervised Vision-Language Modeling for Human Brain Microscopy","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2603.00777","title":"DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.10827","title":"Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.13091","title":"Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2603.25565","title":"GeoHeight-Bench: Towards Height-Aware Multimodal Reasoning in Remote Sensing","created":"2026-03-26","cited_by_count":1,"area":"mllm"},{"id":"2603.26557","title":"MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2605.06158","title":"Stateful Agent Backdoor","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.06638","title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.18607","title":"Forecasting Downstream Performance of LLMs With Proxy Metrics","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.06211","title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.09424","title":"A Sovereign, Open-Source Foundation Model for German and English","created":"2026-07-10","cited_by_count":1,"area":"moe"},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2607.27069","title":"Visual Credit Audit for Multimodal Spatial Reasoning","created":"2026-07-29","cited_by_count":1,"area":"lr"},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.14743","title":"Quantifying the Generation Modality Gap in Speech-Text Language Models","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2609.37577","title":"Pair Difficulty Matters: Rethinking Pairwise LLM-as-a-Judge Evaluation and Consistency","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2610.07643","title":"Monte Carlo Estimation for KV Cache Eviction","created":"2026-10-06","cited_by_count":1,"area":"inference"},{"id":"2610.08559","title":"Latent space bias directions in LLMs capture confidence, not fairness","created":"2026-10-06","cited_by_count":1,"area":"mechinterp"},{"id":"2602.01752","title":"WorldCup Sampling for Multi-bit LLM Watermarking","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2602.02780","title":"Scaling-Aware Adapter for Structure-Grounded LLM Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.14265","title":"STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2603.13759","title":"QTrack: Query-Driven Reasoning for Multi-modal MOT","created":"2026-03-14","cited_by_count":0,"area":"lr"},{"id":"2604.13060","title":"Dental-TriageBench: Benchmarking Multimodal Reasoning for Hierarchical Dental Triage","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2604.27618","title":"Math Education Digital Shadows for Investigating Learning with GenAI: Mathematics Performance, Anxiety, and Confidence in LLMs","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.01870","title":"Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2605.06165","title":"Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.07731","title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2605.08816","title":"Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?","created":"2026-05-09","cited_by_count":0,"area":"agents"},{"id":"2605.11608","title":"PRISM: A Geometric Risk Bound for Decomposing Drift into Scale, Shape, and Head","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.18163","title":"TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.21076","title":"GradeLegal: Automated Grading for German Legal Cases","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.28013","title":"KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2605.31268","title":"Mellum2 Technical Report","created":"2026-05-29","cited_by_count":0,"area":"moe"},{"id":"2606.06714","title":"Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception","created":"2026-06-04","cited_by_count":0,"area":"mllm"},{"id":"2606.09380","title":"Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.14240","title":"AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"id":"2606.15735","title":"EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.19096","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19100","title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.28615","title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.02118","title":"Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03207","title":"S-DiverSe: Spanish Diverse Speech","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.09236","title":"Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem","created":"2026-07-10","cited_by_count":0,"area":"safety"},{"id":"2607.14661","title":"SmartRAG: Native Graph-Based RAG for Mobile Device","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.16214","title":"What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.18819","title":"In-Context Learning for Wound Classification with Small Multimodal Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.27955","title":"SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.03745","title":"Risky Business: Measuring The Faithfulness-Safety Tension","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.05643","title":"Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.09109","title":"Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14629","title":"Inference-Time Mitigation of Adversarial Political Bias in Large Language Models","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.16068","title":"CAPO: Constraint-Aware Prompt Optimization for LLM Agents","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.27461","title":"SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2609.15242","title":"Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain","created":"2026-09-14","cited_by_count":0,"area":"rag"},{"id":"2609.29045","title":"The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning","created":"2026-09-24","cited_by_count":0,"area":"safety"},{"id":"2609.32496","title":"Locally Sound, Globally Insufficient: The Local-Global Gap in Multi-Hop Reasoning","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34742","title":"Do Emotion Concepts Generalize Across Sources, Modalities, and Architectures in Vision-Language Models?","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.35412","title":"Self-Adapting Group of Experts for Multi-Agent Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36920","title":"Benchmarking Automatic Speech Recognition Tools for Iberian Languages","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38958","title":"Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39478","title":"Also Small Models Can Reasonably Self-Evaluate Their Confidence","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39929","title":"RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01093","title":"OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01509","title":"Sharpening Tax in Post-Training","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06345","title":"Breaking Bureaucracy: Evaluating open-source LLMs for legal document review","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07109","title":"JudgeMoE: Distributional Aggregation for LLM-as-a-Judge","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07509","title":"On Open-Ended Information Seeking for Information Elicitation Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}