SONGJUN TU

SONGJUNTU's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 1 day ago

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning

Paper • 2412.09104 • Published Dec 12, 2024

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Paper • 2503.12854 • Published Mar 17

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Paper • 2506.19767 • Published 2 days ago • 11

authored a paper 20 days ago

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL

Paper • 2505.10832 • Published May 16