Zhenxing Mi's picture

Zhenxing Mi

Mifucius

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

upvoted a paper 24 days ago

LongVideoAgent: Multi-Agent Reasoning with Long Videos

upvoted a paper 25 days ago

SemanticGen: Video Generation in Semantic Space

View all activity

Organizations

None yet

Papers 5

arxiv:2511.18922

arxiv:2505.02005

arxiv:2502.10458

arxiv:2411.11374

models 1

Mifucius/ThinkDiff

Updated Sep 7, 2025 • 2

datasets 0

None public yet