Picture for Xiaoran Jin

Xiaoran Jin

ReFT: Reasoning with Reinforced Fine-Tuning

Add code
Jan 17, 2024
Viaarxiv icon

Design of Chain-of-Thought in Math Problem Solving

Add code
Sep 30, 2023
Viaarxiv icon

Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding

Add code
May 16, 2023
Viaarxiv icon