Jie Liu PRO
jieliu
AI & ML interests
Reinforcement Learning, Large Language Model
Recent Activity
upvoted a paper 4 days ago
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation upvoted a paper 27 days ago
dLLM: Simple Diffusion Language Modeling upvoted a paper about 2 months ago
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active ParametersOrganizations
models 13
jieliu/SD3.5M-FlowGRPO-Text-without-KL
Updated • 3
jieliu/SD3.5M-FlowGRPO-PickScore-without-KL
Updated • 1
jieliu/SD3.5M-FlowGRPO-GenEval-without-KL
Updated • 3
jieliu/SD3.5M-FlowGRPO-GenEval
Updated • 214 • 9
jieliu/SD3.5M-FlowGRPO-PickScore
Updated • 135 • 3
jieliu/SD3.5M-FlowGRPO-Text
Updated • 159 • 2
jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-chat-noval-beta0.5-bs24
Updated
jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-chat-math-noval-beta0.5-bs24
Updated
jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-longqa-beta0.5-bs24-seq2048
Updated
jieliu/Qwen2-7B-Instruct-DPO-score-diff-2-longqa-beta0.5-bs24
Updated