Minghao Yan
minghaoyan
AI & ML interests
MLSys
Recent Activity
upvoted
a
paper
about 2 months ago
What Limits Agentic Systems Efficiency?
upvoted
a
paper
2 months ago
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
updated
a model
8 months ago
minghaoyan/wide-llama-829M-compact
Organizations
