Mingyuan Zhou

4 papers University of Texas at Austin

• Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting
• Generative Model Inversion Through the Lens of the Manifold Hypothesis
• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion