{"list":"other","total":60,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"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":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"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":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127},{"id":"2504.00891","title":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning","created":"2025-04-01","cited_by_count":97},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91},{"id":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60},{"id":"2505.16984","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","created":"2025-05-22","cited_by_count":59},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28},{"id":"2505.13026","title":"Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs","created":"2025-05-19","cited_by_count":25},{"id":"2506.01096","title":"SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning","created":"2025-06-01","cited_by_count":18},{"id":"2601.09195","title":"ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection","created":"2026-01-14","cited_by_count":18},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17},{"id":"2506.16029","title":"EvoLM: In Search of Lost Language Model Training Dynamics","created":"2025-06-19","cited_by_count":16},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16},{"id":"2509.23753","title":"Anchored Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":15},{"id":"2509.26628","title":"Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models","created":"2025-09-30","cited_by_count":13},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1}],"next_cursor":null}