Liang Feng
lightslightusc
ยท
AI & ML interests
LLM and VLM
Recent Activity
upvoted
a
paper
about 1 month ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
about 1 month ago
Contamination Detection for VLMs using Multi-Modal Semantic Perturbation