ScienceOne-Math

AI & ML interests

None defined yet.

Recent Activity

SONGJUNTU  authored a paper 1 day ago

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

SONGJUNTU  authored a paper 1 day ago

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

SONGJUNTU  authored a paper 1 day ago

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

View all activity

Team members 5