Kaiwen Hu

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

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

Frequent co-authors

Haoran Xu (1)Somayeh Sojoudi (1)Amy Zhang (1)

Papers (1)

Apr 15, 2026

Haoran Xu +31w ago

Reinforcement Learning via Value Gradient Flow

Forget policy gradients: Value Gradient Flow (VGF) offers a simpler, more scalable way to align LLMs by directly optimizing value functions via optimal transport.

Haoran Xu, Kaiwen Hu, Somayeh Sojoudi +1

RLHF & Preference Learning Training Efficiency & Optimization

Search

Kaiwen Hu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)