{"list":"other","total":50,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2510.18855","title":"Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model","created":"2025-10-21","cited_by_count":55},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50},{"id":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41},{"id":"2504.19599","title":"GVPO: Group Variance Policy Optimization for Large Language Model Post-Training","created":"2025-04-28","cited_by_count":32},{"id":"2509.18851","title":"NGRPO: Negative-enhanced Group Relative Policy Optimization","created":"2025-09-23","cited_by_count":32},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25},{"id":"2509.25849","title":"Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation","created":"2025-09-30","cited_by_count":22},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18},{"id":"2510.05837","title":"EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget","created":"2025-10-07","cited_by_count":14},{"id":"2510.08696","title":"Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting","created":"2025-10-09","cited_by_count":12},{"id":"2608.00782","title":"Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance","created":"2026-08-01","cited_by_count":11},{"id":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10},{"id":"2605.07331","title":"Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective","created":"2026-05-08","cited_by_count":7},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7},{"id":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7},{"id":"2602.02555","title":"Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards","created":"2026-01-30","cited_by_count":6},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6},{"id":"2604.05117","title":"Watch Before You Answer: Learning from Visually Grounded Post-Training","created":"2026-04-06","cited_by_count":5},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3},{"id":"2607.07674","title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","created":"2026-07-08","cited_by_count":3},{"id":"2604.16995","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","created":"2026-04-18","cited_by_count":2},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2},{"id":"2605.28295","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","created":"2026-05-27","cited_by_count":2},{"id":"2602.17677","title":"Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving","created":"2026-01-28","cited_by_count":1},{"id":"2605.05566","title":"Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration","created":"2026-05-07","cited_by_count":1},{"id":"2607.07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","created":"2026-07-08","cited_by_count":1}],"next_cursor":null}