SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
Paper
•
2511.06411
•
Published
•
17
Anyi Li
lianyi00
AI & ML interests
AI4Science, Geometric Deep Learning
Recent Activity
liked
a dataset
about 2 months ago
HR-machine/QM9-Dataset
upvoted
a
paper
7 months ago
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical
Reasoning
Organizations
None yet
upvoted
a
paper
about 2 months ago