Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper
•
2510.03222
•
Published
•
75
Liang Feng
lightslightusc
·
AI & ML interests
LLM and VLM
Recent Activity
upvoted
a
paper
about 2 months ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
about 2 months ago
Contamination Detection for VLMs using Multi-Modal Semantic Perturbation
Organizations
upvoted
2
papers
about 2 months ago