Yu Zhang
yzhangcs
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 17 hours ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
liked
a dataset
2 months ago
yaofu/slimpajama-per-source-length-upsample
upvoted
a
paper
2 months ago
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and
Sketches with TikZ
Organizations
Collections
1
spaces
1
models
0
None public yet
datasets
0
None public yet