就我而言,我一无所知,但满眼的繁星让我入梦。
For my part I know nothing with any certainty, but the sight of the stars makes me dream.
Education
M.S. Computer Science and Technology @ Fudan University, 2023.09 - 2026.06 (expected)
- Advisor: Prof. Qi Zhang & Prof. Tao Gui
B.E. Computer Science and Technology @ Harbin Institute of Technology (Shenzhen), 2019.09 - 2023.06
- GPA (94.26/100) Rank (2/323) CET-4 (599) CET-6 (577)
- Advisor: Prof. Cuiyun Gao
Research Interests
As an early-career researcher, I have great enthusiasm and interest in various fields and am willing to be exposed to new knowledge and challenges.
I am currently focus on 🤖large language models (LLMs), with a particular interest in enhancing the intelligence of models through techniques such as knowledge distillation, reinforcement learning, self-learning and evolution.
I am also interested in 🌐downstream applications of LLMs, including prompt engineering, RAG and agent systems.
Selected Publications
* : Equal contribution. See here for all publications.
Distill Visual Chart Reasoning Ability from LLMs to MLLMs
- Wei He*, Zhiheng Xi*, Wanxu Zhao*, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang
- 📃Preprint Under Review. [Paper] / [Code] / [Dataset] / [Press Release]
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
- Wei He, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
- ✨CCF-B NAACL 2024 Findings. [Paper] / [Code]
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
- Yiwen Ding, Zhiheng Xi, Wei He, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
- 📃Preprint Under Review. [Paper] / [Code]
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
- Yi Lu, Xin Zhou, Wei He, Jun Zhao, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
- ✨CCF-B EMNLP 2024 Findings. [Paper] / [Code] / [Press Release]
LongAgent: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration
- Jun Zhao, Can Zu, Xu Hao, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang
- ✨CCF-B EMNLP 2024 Main. [Paper] / [Dataset] / [Press Release]
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
- Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Dingwen Yang, Chenyang Liao, Xin Guo, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu et al.
- 📃Preprint ⭐300+ Stars Under Review. [Paper] / [Code] / [Project Page] / [Press Release]
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
- Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, Wei He, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang et al.
- 🚀CCF-A ICML 2024. [Paper] / [Code] / [Press Release]
The Rise and Potential of Large Language Model Based Agents: A Survey
- Zhiheng Xi*, Wenxiang Chen*, Xin Guo*, Wei He*, Yiwen Ding*, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang et al.
- 🚀CCF-A 🔥500+ Citation SCIS 2024. [Paper] / [Paperlist] / [Press Release]
TopicAns: Topic-Informed Architecture for Answer Recommendation on Technical Q&A Site
- Yuanhang Yang, Wei He, Cuiyun Gao, Zenglin Xu, Xin Xia, Chuanyi Liu
- 🚀CCF-A TOSEM 2023. [Paper] / [Code]
Experience
Technical Architecture Dept. @ Weixin Group (WXG). Tencent Technology (Shanghai)
- 🔬 NLP Research Intern, advised by Dr. Zifei Shan, 2024.08 - Now
- One paper about MLLM reasoning under review. More works in progress.
AI Application Group @ Futu Holdings. Futu Network Technology (Shenzhen)
- 💻 NLP Engineer Intern, advised by Anjun Zhuang, 2023.03 - 2023.08
- Development for LLM’s downstream applications, such as AI Assistant (RAG) and Topic Detection & Tracking.
STAR Lab @ Harbin Institute of Technology (Shenzhen)
- 🔬 NLP Research Intern, advised by Prof. Cuiyun Gao, 2021.12 - 2023.02
- One paper about NLP for software engineering published.
Selected Honors
[2024] Samsung Scholarship @ Fudan & Samsung (China) Investment Co., Ltd
[2023]🎓Outstanding Graduate @ Harbin Institute of Technology
[2023]🏆The 14th LanQiao Cup C/C++ Programming Contest (Provincial First Prize)
[2023] Huawei Scholarship @ HITSZ & Huawei Technologies Co., Ltd.
[2022] PACT518 Scholarship @ HITSZ & Surfilter Network Technology Co., Ltd.
[2021]🏆American National Mathematical Contest in Modeling (Honorable Mention)
[2021] Gongjin Scholarship @ HITSZ & Shenzhen Gongjin Electronics Co., Ltd.
[2020]🏫National Scholarship @ The China Ministry of Education
[2020]🏆Contemporary Undergraduate Mathematical Contest in Modeling (National First Prize)
About Blog
Recording, producing and creating! Including but not limited to:
- Learning Notes (学习笔记) & Research Notes (科研札记);
- Project Experience (项目经历) & Contest Reviews (比赛回顾);
- Heartfelt Essay (心情随笔)。
Built on Hexo+GitHub, with Fluid theme, continuously optimized and updated.
Click here to visit the Mirror Site (访问镜像站点 - faster access in China, maybe).