The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
Paper
•
2509.07430
•
Published
•
3
•
2
Wei Pang
weipang142857
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
14 days ago
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
upvoted
a
paper
about 1 month ago
Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?
upvoted
a
paper
2 months ago
Computer-Use Agents as Judges for Generative User Interface
Organizations
