CV

Education

• Ph.D in Computer Science, the University of Hong Kong, 2022-2026 (expected)
• M.S. in Computer Science, Peking University, 2019-2022
• B.S. in Computer Science, Peking University, 2015-2019

Work experience

• 03/2024 - 07/2024: NLP Research Intern
  • Sambanova Systems
  • Duties includes: Formal Theorem Proving
  • Supervisor: Yun Du
• 03/2023 - 03/2024: NLP Research Intern
  • Tencent AI Lab
  • Duties included: Mathematics Reasoning and Multi-modal Reasoning
  • Supervisor: Xinting Huang and Wei Bi
• 04/2021 - 10/2022: NLP Research Intern
  • Tencent AI Lab
  • Duties included: Open-domain Dialogue Systems and Neuro-symbolic Reasoning
  • Supervisor: Lemao Liu
• 04/2019 - 07/2020: NLP Research Intern
  • Microsoft STCA
  • Duties included: Retrieval-augmented Dialogue Systems
  • Supervisor: Wei Wu

Publications

SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models

Subgoal-based Demonstration Learning for Formal Theorem Proving

Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue

Delving into Global Dialogue Structures: Structure Planning Augmented Response Selection for Multi-turn Conversations

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions

SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation

On the Compositional Generalization in Versatile Open-domain Dialogue

Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure

There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning

Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation

Learning to Express in Knowledge-Grounded Conversation

There Are a Thousand Hamlets in a Thousand People’s Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory

Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues

Zero-Resource Knowledge-Grounded Dialogue Generation

Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

Low-Resource Knowledge-Grounded Dialogue Generation

A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots

Talks

Conference Proceeding talk 3 on Relevant Topic in Your Field

March 01, 2014

Conference proceedings talk at Testing Institute of America 2014 Annual Conference, Los Angeles, CA

Talk 2 on Relevant Topic in Your Field

February 01, 2014

Talk at London School of Testing, London, UK

Tutorial 1 on Relevant Topic in Your Field

March 01, 2013

Tutorial at UC-Berkeley Institute for Testing Science, Berkeley CA, USA

Talk 1 on Relevant Topic in Your Field

March 01, 2012

Talk at UC San Francisco, Department of Testing, San Francisco, California

Teaching

Teaching experience 2

Teaching experience 1