Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper
•
2601.08763
•
Published
•
141
Yanhan Ye
CoolColoury
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
11 days ago
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
upvoted
a
paper
11 days ago
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
upvoted
a
collection
3 months ago
PCC-Finetuned
Organizations
upvoted
2
papers
11 days ago
upvoted
a
collection
3 months ago
upvoted
an
article
about 1 year ago
Article
Mastering Tensor Dimensions in Transformers
•
132
upvoted
a
paper
almost 2 years ago