About Me

I am a researcher at HunYuan Team, Tencent Inc.

I received my MS degree from the Department of Automation at Tsinghua University, supervised by Prof. Rui Jiang.

I am dedicated to developing interpretable and trustworthy AI models. My current work focuses on advancing the HunYuan models through innovations in data and architecture.

Publications & Preprints

Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought. [Paper]
Tencent Hunyuan Team

One-stop Training of Multiple Capacity Models. [Paper]
Lan Jiang, Haoyang Huang, Dongdong Zhang, Rui Jiang, Furu Wei
Preprint.

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models. [Paper] [Code]
Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Rui Jiang.
EMNLP 2022.

On Length Divergence Bias in Textual Matching Models. [Paper] [Code]
Lan Jiang, Tianshu Lyu, Yankai Lin, Meng Chong, Xiaoyong Lyu, Dawei Yin.
Findings of ACL 2022.

Exploration of the Change Trend Analysis of the Epidemiological History of COVID-19 Patients Based on Natural Language Processing. [Paper]
Xiaolu Fei, Lan Jiang, Pengyu Chen, Jia Li, Lan Wei, Rui Jiang, Hairong Lv.
China Digital Medicine 2020 (Journal).

MAssistant: A Personal Knowledge Assistant for MOOC Learners. The Conference on Empirical Methods in Natural Language Processing. [Paper]
Lan Jiang, Shuhan Hu, Mingyu Huang, Zhichun Wang, Jinjian Yang, Xiaoju Ye, Wei Zheng.
EMNLP 2019.

Education

		Tsinghua University Sep. 2020 - Jun. 2023 Department of Automation Master in Control Science and Engineering Advisor: Rui Jiang
		Beijing Normal University Sept. 2016 - Jun. 2020 College of Information Science and Technology Bachelor in Computer Science and Technology

Experiences

• NLP Engineer at WeType
• Led the “Ask AI” passive recommendation service for WeType, serving about 12M users, ~4.5B daily calls, ~160M daily impressions.
• Research on robustness optimization for RAG

• Research Intern advised by Haoyang Huang
• Study the topic on Mixture of Experts (MoE).

• Research Intern advised by Hao Zhou and Yankan Lin
• Study the topic on the robustness of pre-trained language model

• Algorithm Intern advised by Ruijie Zhang and Min Zeng
• Study the topic on topic-controlled dialogue generation

• Research Intern advised by Tianshu Lyu
• Study the topic on the length divergence bias of textual matching models

Honors & Awards

Teaching Assistantship

Leadership