Yitong Li

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)RLHF & Preference Learning (1)Training Efficiency & Optimization (1)

Frequent co-authors

Junsong Chen (1)Shuchen Xue (1)Pengcuo Zeren (1)Siyuan Fu (1)

Papers (1)

Apr 8, 2026

1w ago·also NVIDIA, HKU

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Scaling diffusion model alignment just got a whole lot cheaper: Sol-RL uses FP4 rollouts to accelerate training convergence by up to 4.64x without sacrificing performance.

Yitong Li, Junsong Chen, Shuchen Xue +8

Multimodal Models RLHF & Preference Learning Training Efficiency & Optimization

Search

Yitong Li

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)