publications

2026

1. 

   A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

   Sophia Tang, Yuchen Zhu, Molei Tao, and Pranam Chatterjee

   Preprint, 2026

   [Paper] [Code]

   rl · dllm · bio

2. 

   Agents' Last Exam

   Agents' Last Exam Team

   Preprint, 2026

   [Paper] [Code] [Website]

   llm · agent

3. 

   FLARE: Diffusion for Hybrid Language Model

   Yuchen Zhu, Jing Shi, Chongjian Ge, Hao Tan, Yiran Xu, Wanrong Zhu, Jason Kuen, Koustava Goswami, Rajiv Jain, Yongxin Chen, Molei Tao, and Jiuxiang Gu

   Preprint, 2026

   [Paper] [Website]

   dllm · llm

4. 

   ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models

   Haotian Xue, Yipu Chen*, Liqian Ma*, Zelin Zhao, Lama Moukheiber, Yuchen Zhu, and Yongxin Chen

   Preprint, 2026

   [Paper] [Code] [Website] [Models]

   diffusion · multimodal

5. 

   Efficient Adjoint Matching for Fine-tuning Diffusion Models

   Jeongwoo Shin*, Dongsoo Shin*, Yuchen Zhu, Wei Guo, Yongxin Chen, Joonseok Lee, Jaewoong Choi, and Jaemoo Choi

   Preprint, 2026

   [Paper]

   rl · diffusion

6. 

   LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

   Shufan Li*, Yuchen Zhu*, Jiuxiang Gu, Kangning Liu, Zhe Lin, Yongxin Chen, Molei Tao, Aditya Grover, and Jason Kuen

   ICML 2026

   [Paper]

   dllm · multimodal · rl

7. 

   Discrete Adjoint Schrödinger Bridge Sampler

   Wei Guo, Yuchen Zhu, Xiaochen Du, Juno Nam, Yongxin Chen, Rafael Gómez-Bombarelli, Guan-Horng Liu, Molei Tao, and Jaemoo Choi

   ICML 2026

   [Paper]

   dllm · sampling

8. 

   Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

   Jaemoo Choi*, Yuchen Zhu*, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, and Yongxin Chen

   ICML 2026

   [Paper]

   rl · diffusion

9. 

   Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

   Jinbin Bai, Yixuan Li, Yuchen Zhu, Yi Xin, Qingyu Shi, Aosong Feng, Xiaohong Liu, Molei Tao, Jianru Xue, Xiangtai Li, and Ming-Hsuan Yang

   ICML 2026

   [Paper]

   dllm · inference

10. 

    Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization

    Yuchen Zhu*, Wei Guo*, Jaemoo Choi, Petr Molodyk, Bo Yuan, Molei Tao, and Yongxin Chen

    ICML 2026 ⭐ Spotlight (< 2.2%)

    [Paper] [Code]

    rl · dllm

2025

1. 

   Proximal Diffusion Neural Sampler

   Wei Guo*, Jaemoo Choi*, Yuchen Zhu, Molei Tao, and Yongxin Chen

   Preprint, 2025

   [Paper]

   sampling · diffusion · dllm

2. 

   MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

   Yuchen Zhu*, Wei Guo*, Jaemoo Choi, Guan-Horng Liu, Yongxin Chen, and Molei Tao

   NeurIPS 2025

   [Paper] [Code]

   sampling · rl · dllm

3. 

   TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

   Sophia Tang*, Yuchen Zhu*, Molei Tao, and Pranam Chatterjee

   Preprint, 2025

   [Paper] [Code]

   rl · dllm · bio

4. 

   Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms

   Yinuo Ren*, Haoxuan Chen*, Yuchen Zhu*, Wei Guo*, Yongxin Chen, Grant M Rotskoff, Molei Tao, and Lexing Ying

   NeurIPS 2025

   [Paper]

   dllm · inference

5. 

   Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models

   Chengyue Huang*, Yuchen Zhu*, Sichen Zhu*, Jingyun Xiao, Moises Andrade, Shivang Chopra, and Zsolt Kira

   ICCV-W 2025

   [Paper]

   vlm · multimodal

6. 

   Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

   Kevin Rojas*, Yuchen Zhu*, Sichen Zhu, Felix Ye, and Molei Tao

   ICML 2025

   [Paper] [Code] [Poster]

   diffusion · dllm · multimodal

7. 

   Learning to Stop: Deep Learning for Mean Field Optimal Stopping

   Lorenzo Magnino*, Yuchen Zhu*, and Mathieu Lauriere

   ICML 2025

   [Paper] [Code] [Poster]

   mf · rl

8. 

   Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups

   Yuchen Zhu*, Tianrong Chen*, Lingkai Kong, Evangelos Theodorou, and Molei Tao

   ICLR 2025

   [Paper] [Code] [Poster]

   diffusion · geometry

9. 

   Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images

   Sichen Zhu*, Yuchen Zhu*, Molei Tao, and Peng Qiu

   ICLR 2025

   [Paper] [Code] [Poster]

   diffusion · bio

10. 

    From Masks to Worlds: A Hitchhiker's Guide to World Models

    Jinbin Bai, Yu Lei, Hecong Wu, Yuchen Zhu, Shufan Li, Yi Xin, Xiangtai Li, Molei Tao, Aditya Grover, and Ming-Hsuan Yang

    Preprint, 2025

    [Paper]

    survey

2024

1. 

   Plug-and-Play Controllable Generation for Discrete Masked Models

   Wei Guo*, Yuchen Zhu*, Molei Tao, and Yongxin Chen

   Preprint, 2024

   [Paper]

   dllm · inference

2. 

   Quantum Generation with Structure Preserving Diffusion Model

   Yuchen Zhu, Tianrong Chen, Evangelos A Theodorou, Xie Chen, and Molei Tao

   Preprint, 2024

   [Paper]

   diffusion · quantum · geometry

3. 

   Deep Learning for Mean Field Optimal Transport

   Sebastian Baudelet^†, Brieuc Frenais^†, Mathieu Lauriere^†, Amal Machtalay^†, and Yuchen Zhu^†

   ESAIM 2024

   [Paper]

   mf

4. 

   A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization

   Yuchen Zhu, Yufeng Zhang, Zhaoran Wang, Zhuoran Yang, and Xiaohong Chen

   Preprint, 2024

   [Paper] [Poster]

   mf · rl