Jie Liu's picture

6 28 9

Jie Liu PRO

jieliu

·

yifan123

AI & ML interests

Reinforcement Learning, Large Language Model

Recent Activity

upvoted a collection about 13 hours ago

upvoted a paper 2 days ago

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

upvoted a paper 9 days ago

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

View all activity

Organizations

Collections 1

Papers 10

arxiv:2509.08826

arxiv:2509.04548

arxiv:2508.21016

arxiv:2505.05470

spaces 1

SD3.5 M Flow GRPO

Generate images from text prompts

models 13

jieliu/SD3.5M-FlowGRPO-Text-without-KL

Updated Jul 22 • 16

jieliu/SD3.5M-FlowGRPO-PickScore-without-KL

Updated Jul 22 • 20

jieliu/SD3.5M-FlowGRPO-GenEval-without-KL

Updated Jul 22 • 1

jieliu/SD3.5M-FlowGRPO-GenEval

Updated May 12 • 772 • 9

jieliu/SD3.5M-FlowGRPO-PickScore

Updated May 11 • 285 • 3

jieliu/SD3.5M-FlowGRPO-Text

Updated May 11 • 145 • 2

jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-chat-noval-beta0.5-bs24

Updated Sep 7, 2024

jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-chat-math-noval-beta0.5-bs24

Updated Sep 7, 2024

jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-longqa-beta0.5-bs24-seq2048

Updated Sep 5, 2024

jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-longqa-beta0.5-bs24

Updated Sep 5, 2024

datasets 2

jieliu/counting_edit

Viewer • Updated Aug 5 • 310 • 64

jieliu/homepage

Viewer • Updated Feb 10 • 4 • 322