{"total":661,"rows":[{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"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,"area":"lr"},{"id":"2511.22699","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","created":"2025-11-27","cited_by_count":277,"area":"diffusion"},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259,"area":"diffusion"},{"id":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253,"area":null},{"id":"2509.20427","title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","created":"2025-09-24","cited_by_count":249,"area":"inference"},{"id":"2509.16117","title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process","created":"2025-09-19","cited_by_count":230,"area":"diffusion"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192,"area":"diffusion"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.21802","title":"MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE","created":"2025-07-29","cited_by_count":178,"area":"diffusion"},{"id":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2508.04324","title":"TempFlow-GRPO: When Timing Matters for GRPO in Flow Models","created":"2025-08-06","cited_by_count":97,"area":"lr"},{"id":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92,"area":"lr"},{"id":"2512.04678","title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","created":"2025-12-04","cited_by_count":86,"area":null},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85,"area":"wm"},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80,"area":"alignment"},{"id":"2510.15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset","created":"2025-10-17","cited_by_count":79,"area":null},{"id":"2510.16888","title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","created":"2025-10-19","cited_by_count":79,"area":"alignment"},{"id":"2511.09515","title":"WMPO: World Model-based Policy Optimization for Vision-Language-Action Models","created":"2025-11-12","cited_by_count":70,"area":"wm"},{"id":"2509.08826","title":"RewardDance: Reward Scaling in Visual Generation","created":"2025-09-10","cited_by_count":68,"area":"alignment"},{"id":"2509.25050","title":"Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models","created":"2025-09-29","cited_by_count":67,"area":"diffusion"},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2509.23909","title":"EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling","created":"2025-09-28","cited_by_count":64,"area":"alignment"},{"id":"2509.06040","title":"BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models","created":"2025-09-07","cited_by_count":61,"area":"diffusion"},{"id":"2509.05952","title":"Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching","created":"2025-09-07","cited_by_count":56,"area":"diffusion"},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54,"area":"diffusion"},{"id":"2511.13649","title":"Distribution Matching Distillation Meets Reinforcement Learning","created":"2025-11-17","cited_by_count":50,"area":"diffusion"},{"id":"2510.22319","title":"GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping","created":"2025-10-25","cited_by_count":49,"area":"lr"},{"id":"2505.20147","title":"FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities","created":"2025-05-26","cited_by_count":46,"area":"mllm"},{"id":"2509.04548","title":"Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model","created":"2025-09-04","cited_by_count":41,"area":null},{"id":"2505.13934","title":"RLVR-World: Training World Models with Reinforcement Learning","created":"2025-05-20","cited_by_count":40,"area":"wm"},{"id":"2605.15055","title":"DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models","created":"2026-05-14","cited_by_count":40,"area":"diffusion"},{"id":"2512.23464","title":"HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation","created":"2025-12-29","cited_by_count":36,"area":"diffusion"},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36,"area":null},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"id":"2605.08063","title":"Flow-OPD: On-Policy Distillation for Flow Matching Models","created":"2026-05-08","cited_by_count":34,"area":"diffusion"},{"id":"2605.11061","title":"HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer","created":"2026-05-11","cited_by_count":32,"area":null},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32,"area":"mllm"},{"id":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31,"area":"lr"},{"id":"2509.06942","title":"Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference","created":"2025-09-08","cited_by_count":30,"area":"diffusion"},{"id":"2510.04573","title":"LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning","created":"2025-10-06","cited_by_count":29,"area":"lr"},{"id":"2602.05993","title":"Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps","created":"2026-02-05","cited_by_count":29,"area":"diffusion"},{"id":"2506.18564","title":"VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning","created":"2025-06-23","cited_by_count":26,"area":null},{"id":"2510.18701","title":"UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation","created":"2025-10-21","cited_by_count":25,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2512.21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation","created":"2025-12-24","cited_by_count":24,"area":null},{"id":"2602.09022","title":"WorldCompass: Reinforcement Learning for Long-Horizon World Models","created":"2026-02-09","cited_by_count":24,"area":"wm"},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24,"area":"diffusion"},{"id":"2508.21066","title":"OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning","created":"2025-08-28","cited_by_count":23,"area":"alignment"},{"id":"2601.23286","title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","created":"2026-01-30","cited_by_count":23,"area":"diffusion"},{"id":"2508.06924","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning","created":"2025-08-09","cited_by_count":22,"area":"lr"},{"id":"2605.05204","title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","created":"2026-05-06","cited_by_count":22,"area":"diffusion"},{"id":"2507.23675","title":"One-Step Flow Policy Mirror Descent","created":"2025-07-31","cited_by_count":21,"area":"diffusion"},{"id":"2510.01982","title":"Fine-Grained GRPO for Precise Preference Alignment in Flow Models","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2601.20218","title":"DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment","created":"2026-01-28","cited_by_count":21,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2510.24474","title":"Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling","created":"2025-10-28","cited_by_count":20,"area":null},{"id":"2602.03139","title":"Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis","created":"2026-02-03","cited_by_count":20,"area":null},{"id":"2601.19834","title":"Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models","created":"2026-01-27","cited_by_count":19,"area":"wm"},{"id":"2605.10759","title":"Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models","created":"2026-05-11","cited_by_count":19,"area":"diffusion"},{"id":"2509.23352","title":"Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling","created":"2025-09-27","cited_by_count":18,"area":"diffusion"},{"id":"2510.11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment","created":"2025-10-13","cited_by_count":18,"area":"lr"},{"id":"2512.24146","title":"Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning","created":"2025-12-30","cited_by_count":18,"area":"diffusion"},{"id":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2509.25170","title":"GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models","created":"2025-09-29","cited_by_count":17,"area":"diffusion"},{"id":"2511.20549","title":"Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning","created":"2025-11-25","cited_by_count":17,"area":"diffusion"},{"id":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"area":"lr"},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17,"area":"deeprl"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2510.25889","title":"$\\pi_\\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models","created":"2025-10-29","cited_by_count":16,"area":"vla"},{"id":"2511.16955","title":"Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models","created":"2025-11-21","cited_by_count":16,"area":"alignment"},{"id":"2512.16906","title":"VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization","created":"2025-12-18","cited_by_count":16,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2509.16197","title":"MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer","created":"2025-09-19","cited_by_count":15,"area":"mllm"},{"id":"2509.25027","title":"STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2601.10332","title":"Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders","created":"2026-01-15","cited_by_count":15,"area":"lr"},{"id":"2602.20903","title":"TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering","created":"2026-02-24","cited_by_count":15,"area":null},{"id":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"area":"lr"},{"id":"2603.24587","title":"DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving","created":"2026-03-25","cited_by_count":15,"area":"wm"},{"id":"2605.00416","title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","created":"2026-05-01","cited_by_count":15,"area":"vla"},{"id":"2605.14696","title":"EponaV2: Driving World Model with Comprehensive Future Reasoning","created":"2026-05-14","cited_by_count":15,"area":"wm"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2509.25171","title":"TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion","created":"2025-09-29","cited_by_count":14,"area":"diffusion"},{"id":"2510.08425","title":"Reinforcing Diffusion Models by Direct Group Preference Optimization","created":"2025-10-09","cited_by_count":14,"area":"lr"},{"id":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"area":"lr"},{"id":"2510.21583","title":"Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization","created":"2025-10-24","cited_by_count":14,"area":"lr"},{"id":"2511.19428","title":"Flow Map Distillation Without Data","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2601.00423","title":"E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models","created":"2026-01-01","cited_by_count":14,"area":"lr"},{"id":"2602.12205","title":"DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2602.23783","title":"Diffusion Probe: Generated Image Result Prediction Using CNN Probes","created":"2026-02-27","cited_by_count":14,"area":"diffusion"},{"id":"2603.17808","title":"EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards","created":"2026-03-18","cited_by_count":14,"area":"wm"},{"id":"2604.11626","title":"RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time","created":"2026-04-13","cited_by_count":14,"area":"alignment"},{"id":"2606.27377","title":"DanceOPD: On-Policy Generative Field Distillation","created":"2026-06-25","cited_by_count":14,"area":"diffusion"},{"id":"2509.09666","title":"Unified Multimodal Models as Auto-Encoders","created":"2025-09-11","cited_by_count":13,"area":null},{"id":"2509.23958","title":"Reinforcement Learning with Inverse Rewards for World Model Post-training","created":"2025-09-28","cited_by_count":13,"area":"wm"}],"next_cursor":"100"}