{"list":"other","total":117,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"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":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"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":"2501.12326","title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents","created":"2025-01-21","cited_by_count":610},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2408.15240","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","created":"2024-08-27","cited_by_count":480},{"id":"2406.06592","title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","created":"2024-06-05","cited_by_count":441},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2501.05366","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","created":"2025-01-09","cited_by_count":433},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"id":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2501.03262","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","created":"2025-01-04","cited_by_count":241},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2412.01981","title":"Free Process Rewards without Process Labels","created":"2024-12-02","cited_by_count":165},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110},{"id":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106},{"id":"2402.04248","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","created":"2024-02-06","cited_by_count":105},{"id":"2408.02442","title":"Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models","created":"2024-08-05","cited_by_count":96},{"id":"2501.10893","title":"Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments","created":"2025-01-18","cited_by_count":95},{"id":"2407.16216","title":"Reinforcement Learning for LLM Post-Training: A Survey","created":"2024-07-23","cited_by_count":92},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2410.11325","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","created":"2024-10-15","cited_by_count":90},{"id":"2411.02265","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","created":"2024-11-04","cited_by_count":90},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87},{"id":"2308.05960","title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","created":"2023-08-11","cited_by_count":84},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83},{"id":"2403.15360","title":"SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series","created":"2024-03-22","cited_by_count":82},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71},{"id":"2309.08958","title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","created":"2023-09-16","cited_by_count":60},{"id":"2401.04081","title":"MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts","created":"2024-01-08","cited_by_count":60},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"2501.09891","title":"Evolving Deeper LLM Thinking","created":"2025-01-17","cited_by_count":58},{"id":"2501.19306","title":"SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling","created":"2025-01-31","cited_by_count":54},{"id":"2501.14342","title":"Chain-of-Retrieval Augmented Generation","created":"2025-01-24","cited_by_count":49},{"id":"2503.04625","title":"START: Self-taught Reasoner with Tools","created":"2025-03-06","cited_by_count":47},{"id":"2406.17744","title":"Following Length Constraints in Instructions","created":"2024-06-25","cited_by_count":46},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46},{"id":"2410.10630","title":"Thinking LLMs: General Instruction Following with Thought Generation","created":"2024-10-14","cited_by_count":45},{"id":"2407.02552","title":"RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs","created":"2024-07-02","cited_by_count":43},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43},{"id":"2407.02524","title":"Meta Large Language Model Compiler: Foundation Models of Compiler Optimization","created":"2024-06-27","cited_by_count":39},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38},{"id":"2501.01028","title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model","created":"2025-01-02","cited_by_count":36},{"id":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35},{"id":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33},{"id":"2410.01748","title":"Not All LLM Reasoners Are Created Equal","created":"2024-10-02","cited_by_count":30},{"id":"2408.10681","title":"HMoE: Heterogeneous Mixture of Experts for Language Modeling","created":"2024-08-20","cited_by_count":29}],"next_cursor":"100"}