Jingquan Wang — accepted AI-conference papers

2026

R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning

Yongchao Chen, Yueying Liu, Junwei Zhou, Yilun Hao, Jingquan Wang, Yang Zhang +2

ICLR 2026poster

Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate…

Cited by 0 Source ↗Scholar ↗

2022

Semantically Proportional Patchmix for Few-Shot Learning

Jingquan Wang, Jing Xu, Yu Pan, Zenglin Xu

ICASSP 2022accepted

Few-shot learning aims to classify unseen classes with only a limited number of labeled data. Recent works have demonstrated that training models with a simple transfer learning strategy can achieve competitive results in few-shot classification. Although excelling at distinguishing training data, t…

Cited by 0 Source ↗Scholar ↗