scuuy
scuuy666
AI & ML interests
Data Centric LLM / MLLM
Application
MCP
Recent Activity
upvoted
a
paper
about 20 hours ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
upvoted
a
paper
about 20 hours ago
mHC: Manifold-Constrained Hyper-Connections