Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
Paper
•
2512.06533
•
Published
•
6
tangsheng
simonts
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
22 days ago
P1: Mastering Physics Olympiads with Reinforcement Learning
Organizations
None yet
upvoted
a
paper
1 day ago