Jingjing Xu

Improving Formal Reasoning of Transformer with State Stack

Fourier Analysis Network

Why Does the Effective Context Length of LLMs Fall Short?

Teaching Language Models to Critique via Reinforcement Learning

Let the Code LLM Edit Itself When You Edit the Code

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code

FAN: Fourier Analysis Networks

Empowering Large Language Model Agents through Action Learning

LegoMT2: Non-Blocking Federated Learning for Massive Multilingual Machine Translation

Extrapolating Large Language Models to Non-English by Aligning Languages