2026 顶会论文
8作者位次 #4/5ICLR 2026Poster· Optimization / Sampling and Optimization
Proximal Diffusion Neural Sampler
Wei Guo · Jaemoo Choi · Yuchen Zhu · Molei Tao · Yongxin Chen
作者位次 #3/4ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Provable Separations between Memorization and Generalization in Diffusion Models
Zeqi Ye · Qijie Zhu · Molei Tao · Minshuo Chen
作者位次 #6/7ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Generalization of Diffusion Models Arises with a Balanced Representation Space
Zekai Zhang · Xiao Li · Xiang Li · Lianghe Shi · Meng Wu · Molei Tao · Qing Qu
作者位次 #2/7ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport
Lingkai Kong · Molei Tao · Yang Liu · Bryan Wang · Jinmiao Fu · Chien-Chih Wang · Huidong Liu
作者位次 #6/7ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Kevin Rojas · Jiahe Lin · Kashif Rasul · Anderson Schneider · Yuriy Nevmyvaka · Molei Tao · Wei Deng
作者位次 #3/3ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
What Exactly Does Guidance Do in Masked Discrete Diffusion Models
Ye He · Kevin Rojas · Molei Tao
作者位次 #6/6ICLR 2026Poster· Deep Learning / Generative Models and Autoencoders
Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
Kevin Rojas · Ye He · Chieh-Hsin Lai · Yuhta Takida · Yuki Mitsufuji · Molei Tao
作者位次 #2/3ICLR 2026Poster· Theory / Probabilistic Methods
Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
Wei Guo · Molei Tao · Yongxin Chen