{"list":"other","total":109,"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"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":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"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":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"2412.06769","title":"Training Large Language Models to Reason in a Continuous Latent Space","created":"2024-12-09","cited_by_count":797},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"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":"2508.15487","title":"Dream 7B: Diffusion Large Language Models","created":"2025-08-21","cited_by_count":544},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"id":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301},{"id":"2505.19223","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","created":"2025-05-25","cited_by_count":285},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281},{"id":"2505.15809","title":"MMaDA: Multimodal Large Diffusion Language Models","created":"2025-05-21","cited_by_count":250},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236},{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206},{"id":"2404.15758","title":"Let's Think Dot by Dot: Hidden Computation in Transformer Language Models","created":"2024-04-24","cited_by_count":191},{"id":"2506.20639","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","created":"2025-06-25","cited_by_count":187},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178},{"id":"2508.02193","title":"Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference","created":"2025-08-04","cited_by_count":178},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138},{"id":"2506.10892","title":"The Diffusion Duality","created":"2025-06-12","cited_by_count":135},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119},{"id":"2505.15778","title":"Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space","created":"2025-05-21","cited_by_count":117},{"id":"2503.22342","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","created":"2025-03-28","cited_by_count":96},{"id":"2509.06949","title":"Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models","created":"2025-09-08","cited_by_count":88},{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83},{"id":"2509.01142","title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","created":"2025-09-01","cited_by_count":81},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80},{"id":"2505.12514","title":"Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought","created":"2025-05-18","cited_by_count":77},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67},{"id":"2509.05952","title":"Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching","created":"2025-09-07","cited_by_count":56},{"id":"2505.10446","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","created":"2025-05-15","cited_by_count":54},{"id":"2503.19595","title":"Optimizing Language Models for Inference Time Objectives using Reinforcement Learning","created":"2025-03-25","cited_by_count":53},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49},{"id":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41},{"id":"2510.09541","title":"SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models","created":"2025-10-10","cited_by_count":41},{"id":"2509.02333","title":"DCPO: Dynamic Clipping Policy Optimization","created":"2025-09-02","cited_by_count":40},{"id":"2502.01384","title":"Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods","created":"2025-02-03","cited_by_count":38},{"id":"2508.03440","title":"LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking","created":"2025-08-05","cited_by_count":38},{"id":"2505.23648","title":"Continuous Chain of Thought Enables Parallel Exploration and Reasoning","created":"2025-05-29","cited_by_count":35},{"id":"2509.19170","title":"Soft Tokens, Hard Truths","created":"2025-09-23","cited_by_count":35},{"id":"2512.03759","title":"Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective","created":"2025-12-03","cited_by_count":34},{"id":"2510.08554","title":"Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization","created":"2025-10-09","cited_by_count":33},{"id":"2510.03206","title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","created":"2025-10-03","cited_by_count":32},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28},{"id":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27},{"id":"2506.21170","title":"Cosmos: Compressed and Smooth Latent Space for Text Diffusion Modeling","created":"2025-06-26","cited_by_count":25},{"id":"2405.08644","title":"Thinking Tokens for Language Modeling","created":"2024-05-14","cited_by_count":24},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22},{"id":"2503.15952","title":"Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning","created":"2025-03-20","cited_by_count":21},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21},{"id":"2409.08561","title":"Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding","created":"2024-09-13","cited_by_count":19},{"id":"2502.08482","title":"Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning","created":"2025-02-12","cited_by_count":19},{"id":"2510.02212","title":"DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning","created":"2025-10-02","cited_by_count":19},{"id":"2412.02674","title":"Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models","created":"2024-12-03","cited_by_count":18},{"id":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18},{"id":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17},{"id":"2601.08808","title":"Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge","created":"2026-01-13","cited_by_count":16}],"next_cursor":"100"}