{"total":542,"rows":[{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2602.06053","title":"PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models","created":"2026-01-14","cited_by_count":63,"area":null},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62,"area":null},{"id":"2510.06477","title":"Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin","created":"2025-10-07","cited_by_count":52,"area":null},{"id":"2509.13312","title":"WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research","created":"2025-09-16","cited_by_count":46,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2509.21305","title":"Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs","created":"2025-09-25","cited_by_count":37,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2509.18101","title":"A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services","created":"2025-08-30","cited_by_count":17,"area":null},{"id":"2511.18850","title":"Cognitive Alpha Mining via LLM-Driven Code-Based Evolution","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2510.10397","title":"AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2602.11287","title":"HiFloat4 Format for Language Model Inference","created":"2026-02-11","cited_by_count":11,"area":null},{"id":"2604.06996","title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","created":"2026-04-08","cited_by_count":11,"area":null},{"id":"2604.10098","title":"Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation","created":"2026-04-11","cited_by_count":11,"area":null},{"id":"2509.04292","title":"Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?","created":"2025-09-04","cited_by_count":10,"area":null},{"id":"2510.11389","title":"Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies","created":"2025-10-13","cited_by_count":10,"area":null},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2604.23530","title":"MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings","created":"2026-04-26","cited_by_count":10,"area":null},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2511.13027","title":"Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection","created":"2025-11-17","cited_by_count":9,"area":null},{"id":"2511.19413","title":"UniGame: Turning a Unified Multimodal Model Into Its Own Adversary","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2602.08071","title":"ViT-5: Vision Transformers for The Mid-2020s","created":"2026-02-08","cited_by_count":9,"area":null},{"id":"2603.06612","title":"Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness","created":"2026-02-20","cited_by_count":9,"area":null},{"id":"2603.08823","title":"Fish Audio S2 Technical Report","created":"2026-03-09","cited_by_count":9,"area":null},{"id":"2603.21524","title":"CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs","created":"2026-03-23","cited_by_count":9,"area":null},{"id":"2605.26302","title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","created":"2026-05-25","cited_by_count":9,"area":null},{"id":"2606.02461","title":"AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents","created":"2026-06-01","cited_by_count":9,"area":null},{"id":"2510.05969","title":"Probing the Difficulty Perception Mechanism of Large Language Models","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2510.09017","title":"Value-State Gated Attention for Mitigating Extreme-Token Phenomena in Transformers","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2604.07466","title":"Cross-Tokenizer LLM Distillation through a Byte-Level Interface","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2510.07073","title":"VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2510.07985","title":"Fewer Weights, More Problems: A Practical Attack on LLM Pruning","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2510.19600","title":"Human-Agent Collaborative Paper-to-Page Crafting","created":"2025-10-22","cited_by_count":7,"area":null},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2601.02702","title":"MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration","created":"2026-01-06","cited_by_count":7,"area":null},{"id":"2601.18067","title":"EvolVE: Evolutionary Search for LLM-based Verilog Generation and Optimization","created":"2026-01-26","cited_by_count":7,"area":null},{"id":"2602.07824","title":"Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training","created":"2026-02-08","cited_by_count":7,"area":null},{"id":"2602.10144","title":"When LLMs get significantly worse: A statistical approach to detect model degradations","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2602.21456","title":"Revisiting Text Ranking in Deep Research","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2603.28589","title":"Towards a Medical AI Scientist","created":"2026-03-30","cited_by_count":7,"area":null},{"id":"2604.03216","title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","created":"2026-04-03","cited_by_count":7,"area":null},{"id":"2604.11543","title":"NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment","created":"2026-04-13","cited_by_count":7,"area":null},{"id":"2508.20907","title":"Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant","created":"2025-08-28","cited_by_count":6,"area":null},{"id":"2602.02219","title":"Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.13273","title":"MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2603.03308","title":"Old Habits Die Hard: How Conversational History Geometrically Traps LLMs","created":"2026-02-08","cited_by_count":6,"area":null},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2605.30232","title":"How's it going? Reinforcement learning in language models recruits a functional welfare axis","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2607.18235","title":"Automated Discovery Has No Universally Superior Harness","created":"2026-07-20","cited_by_count":6,"area":null},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2601.00282","title":"Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2601.09527","title":"Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2602.07549","title":"When Is Enough Not Enough? Illusory Completion in Search Agents","created":"2026-02-07","cited_by_count":5,"area":null},{"id":"2602.15344","title":"ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2602.24287","title":"Do LLMs Benefit From Their Own Words?","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2605.20767","title":"The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study","created":"2026-05-20","cited_by_count":5,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2608.20169","title":"Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection","created":"2026-08-20","cited_by_count":5,"area":null},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.09159","title":"Cross-Representation Benchmarking in Time-Series Electronic Health Records for Clinical Outcome Prediction","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2510.11313","title":"Automated Skill Decomposition Meets Expert Ontologies: Bridging the Granularity Gap with LLMs","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2511.22490","title":"SciPostGen: Bridging the Gap between Scientific Papers and Poster Layouts","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2512.01224","title":"CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.10206","title":"CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2512.20823","title":"NotSoTiny: A Large, Living Benchmark for RTL Code Generation","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2601.00260","title":"TotalFM: An Organ-Separated 3D-CT Foundation Model Leveraging Large-Scale Routine Clinical Radiology Data","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2602.00070","title":"FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.11700","title":"TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2602.12394","title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2602.14696","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2603.12226","title":"Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2604.00002","title":"Benchmark for Assessing Olfactory Perception of Large Language Models","created":"2026-03-08","cited_by_count":4,"area":null},{"id":"2604.07650","title":"A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.02815","title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2605.22175","title":"SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2605.25704","title":"PowLU: An Activation Function for Stable Pre-Training of LLMs","created":"2026-05-25","cited_by_count":4,"area":null},{"id":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2608.06867","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","created":"2026-08-07","cited_by_count":4,"area":null},{"id":"2509.06770","title":"Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2510.06780","title":"Foundations of LLM Knowledge Materialization: Termination, Reproducibility, Robustness","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.06949","title":"Grouped Differential Attention","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2511.00092","title":"QuantumBench: A Benchmark for Quantum Problem Solving","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2511.05313","title":"Controllably Efficient Language Models","created":"2025-11-07","cited_by_count":3,"area":null}],"next_cursor":"100"}