Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
Paper
•
2602.06422
•
Published
•
32
Jinluan Yang
yangjinluan
AI & ML interests
Trustworthy Machine Learning
Recent Activity
upvoted
a
paper
about 4 hours ago
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
upvoted
a
paper
5 days ago
Can Tool-Integrated Reinforcement Learning Generalize Across Diverse Domains?
authored
a paper
6 days ago
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Organizations
upvoted
a
paper
about 4 hours ago
upvoted
a
paper
5 days ago
upvoted
3
papers
6 days ago
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
Paper
•
2602.03048
•
Published
•
33
V_0: A Generalist Value Model for Any Policy at State Zero
Paper
•
2602.03584
•
Published
•
21
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Paper
•
2601.22642
•
Published
•
9
upvoted
a
paper
15 days ago