RL for Generative Models

RL: Reinforcement Learning

Ask about this topic

Momentum

12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 94

All topics
CardsList

  1. Variance-Averse nn-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments

    Oct 6, 2026Guhyeon Kang, Minhae KwonDistributional RLRisk-Sensitive RL

    Department of Electrical and Computer Engineering Sungkyunkwan University, Republic of Korea

  2. Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning

    Oct 6, 2026Zhijun Zhang, Qianlong Wang, Keyang Ding +5Adversarial TrainingArgument Mining

    College of Applied Science, Shenzhen University, Shenzhen, China · School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China · Harbin Institute of Technology (Shenzhen), Shenzhen, China +2

  3. MEND: RL For Flow Models via Proximal Velocity Matching

    Oct 5, 2026Shreshth Saini, Neil Birkbeck, Yilin Wang +2Flow MatchingRL for Image Generation

    The University of Texas at Austin · Google · University of Colorado Boulder

  4. Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features

    Oct 1, 2026Jason X. Liu, Sebastian Ibarraran, Frank Hu +7Autoregressive Language ModelingSparse Autoencoders

    Stanford University

  5. Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization

    Oct 1, 2026Zhen Zhou, Zhiwei Ning, Puhua Jiang +6Flow Matching3D Mesh Generation

    Tencent Hunyuan · Shanghai Jiao Tong University · Communication University of China

  6. FutureWorlds: Learning Robotic World Models from Alternative Futures

    Oct 1, 2026Hao Wu, Shengju Qian, Weiyan Wang +5Action-Conditioned Video GenerationWorld Model Learning

    HKUST (GZ) · CUHK · Tencent +3

  7. RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation

    Sep 29, 2026Zixuan Yang, Yiqun Chen, Qi Liu +6Open-Ended GenerationReward Modeling

    Renmin University of China · University of Southern California · Xiaohongshu Inc.

  8. Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models

    Sep 28, 2026Wentao Zhou, Weijie Gan, Jiayun WangAdversarial TrainingUnified Multimodal Models

    Georgia Institute of Technology · Washington University in St. Louis

  9. Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL

    Sep 26, 2026Qinwei Ma, Jingzhe Shi, Simin Fan +2RL for Image GenerationAdaptive Loss Weighting

    College of AI, Tsinghua University · Department of Electrical and Computer Engineering, Princeton University · EPFL +1

  10. PoEM: Predicting RL Outcomes from Existing Policies

    Sep 24, 2026Kimia Hamidieh, Giannis Daras, Antonio TorralbaRL for Generative ModelsRL Post-Training

    MIT CSAIL

  11. AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

    Sep 24, 2026Zhiyu Xu, Weilong Yan, Yufei Shi +4Audio-Video GenerationAudio-Visual Alignment

    Shanghai AI Laboratory · The Hong Kong Polytechnic University · National University of Singapore +2

  12. WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps

    Sep 22, 2026Abbas Mammadov, Jerry Y. Huang, Justin Lin +5Reinforcement LearningGenerative Flow Networks

    University of Oxford · Carnegie Mellon University

  13. UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising

    Sep 17, 2026Kun Yao, Yuhang Zhou, Yichi Zhang +6Online AdvertisingGenerative Retrieval

    Meituan, Beijing, China

  14. Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy

    Sep 11, 2026Pengfei Zhang, Teng Sun, Xianchao XiuLatent Action LearningRobot Policy Learning

    School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China

  15. Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer

    Sep 7, 2026Zhiwei Ning, Zhen Zhou, Puhua Jiang +73D Mesh GenerationDiffusion Model Distillation

  16. Tail-Likelihood Reinforcement Learning

    Sep 2, 2026Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar +11Risk-Sensitive RLRL for Generative Models

    Carnegie Mellon University · Together AI · University of California, Berkeley +2

  17. HCGRec: Hint-Conditioned Generative Recommendation with Semantic IDs

    Aug 12, 2026Kangning Zhang, Haotian Fang, Xukun Luo +6Sequential RecommendationRecommender Systems

    Shanghai Jiao Tong University Shanghai, China · Mei Tuan Beijing, China

  18. Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning

    Aug 6, 2026Farzana NasrinRL for Generative ModelsPersistent Homology

    Department of Mathematics, University of Tennessee, Knoxville, TN -37916, USA

  19. iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

    Aug 6, 2026Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel +2Constrained Generative ModelingAgentic RL

    Pulchowk Campus, IOE, Tribhuvan University, Lalitpur, Nepal · INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria · NAAMII, Kathmandu, Nepal

  20. LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction

    Aug 6, 2026Yingqing Guo, Hui Yuan, Zijian He +2RL for Video GenerationRL for Image Generation

  21. GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model

    Aug 4, 2026Guanrou Yang, Tian Tan, Qian Chen +8Flow MatchingTTS Synthesis

    Shanghai Jiao Tong University · Shanghai Innovation Institute · Independent Researcher +2

  22. Reinforcement Learning: From Algorithms To Foundation Models

    Jul 20, 2026Zihan DingReinforcement LearningRL for Video Generation

    Department of Electrical Computer Engineering, Princeton University

  23. VINE: Taming Generative Control Policies for Reinforcement Learning

    Jul 11, 2026Rushuai Yang, Zhuo Han, Houlin Li +10RL for RoboticsOffline RL

    1AgiBot · 3Peking University · 2The Hong Kong University of Science and Technology

  24. Optimizing Visual Generative Models via Distribution-wise Rewards

    Jul 2, 2026Ruihang Li, Mengde Xu, Shuyang Gu +4Diffusion Model Fine-TuningRL for Image Generation

    University of Science and Technology of China · Shanghai Innovation Institute · Hunyuan Frontier Lab, Tencent +1

  25. Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

    Jul 1, 2026Zhiqi Li, Wen Zhang, Bo ZhuImage GenerationFlow Map Learning

    Georgia Institute of Technology, Atlanta, GA, USA.

  26. FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

    Jun 29, 2026Zheming Fu, Ruizhe He, Wei Shang +4Flow MatchingGenerative Modeling

    Beihang University · Joy Future Academy · Zhongguancun Academy +2

  27. PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction

    Jun 26, 2026Dongxia Wu, Mingyu Li, Yuhui Zhang +4Single-Cell Perturbation ModelingReinforcement Learning with Verifiable Rewards

    Peking University Beijing, China · Stanford University Stanford, CA

  28. Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN

    Jun 25, 2026Archer Moore, Mingming Gong, Liam Hodgkinson3D Shape GenerationRL for Generative Models

    School of Mathematics and Statistics, The University of Melbourne, Parkville, VIC 3010, Australia

  29. Scaling Multi-Reference Image Generation with Dynamic Reward Optimization

    Jun 25, 2026Wenwang Huang, Yusen Fu, Junjie Wang +6Image GenerationRL for Generative Models

    Harbin Institute of Technology, Shenzhen · Independent Researcher · Shenzhen Loop Area Institute

  30. Uncertainty-aware reinforcement learning for chemical language models

    Jun 23, 2026Borja Medina, Jon Paul JanetMolecular GenerationRL for Generative Models

    Molecular AI, Discovery Sciences, BioPharmaceuticals R&D AstraZeneca AB Gothenburg, Sweden