Runze Liu's picture

1

Runze Liu

RyanLiu112

·

https://ryanliu112.github.io

AI & ML interests

LLM, RL, RLHF

Recent Activity

authored a paper 4 days ago

SEABO: A Simple Search-Based Method for Offline Imitation Learning

authored a paper 5 days ago

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

authored a paper 5 days ago

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

View all activity

Organizations

Papers 5

arxiv:2502.06703

arxiv:2412.10713

arxiv:2410.14660

arxiv:2402.03807

models

None public yet

datasets

None public yet