Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper
•
2510.03222
•
Published
•
75
cxdxcqwx
afcawd
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 months ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
6 months ago
USO: Unified Style and Subject-Driven Generation via Disentangled and
Reward Learning
liked
a model
6 months ago
bytedance-research/USO
Organizations
