today local_bar

Mingyuan Zhou

Researcher, Microsoft

4 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

#508 · Yifan Sun, Jingyan Shen, Yibin Wang, Tianyu Chen, Zhendong Wang, Mingyuan Zhou, Huan Zhang

We propose two techniques to improve the data efficiency of LLM RL fine-tuning: difficulty-targeted online data selection and rollout replay.

Generative Model Inversion Through the Lens of the Manifold Hypothesis

#1300 · Xiong Peng, Bo Han, Fengfei Yu, Tongliang Liu, Feng Liu, Mingyuan Zhou

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

#2606 · Ruyi An, Haicheng Huang, Huangjie Zheng, Mingyuan Zhou

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

#5518 Spotlight · Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, Eli Shechtman

We introduce a new method to train autoregressive video diffusion models by performing autoregressive self-rollout with KV caching during training.