Huayu Chen

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression

Exploratory Diffusion Model for Unsupervised Reinforcement Learning

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

Discrete Diffusion Trajectory Alignment via Stepwise Decomposition

Process Reinforcement through Implicit Rewards

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Visual Generation Without Guidance

Free Process Rewards without Process Labels