CV

PhD

• Research focus: memory-augmented dialogue systems, long-term memory modeling.
• Core courses: NLP, Machine Learning Theory.

M.Sc. in Computer Science and Technology

• Graduated Top 10%.
• Courses: Machine Learning, Deep Learning, NLP.

B.Eng. in Software Engineering

• Graduated Top 30%.
• Courses: Data Structure, OS, Algorithm Design.

Visiting Researcher

• Memory in LLM-Agent, Temporal Reasoning.

Research Intern

• CoT Reasoning Data Generation.
• Model Editing

Visiting Researcher

• RAG
• Personal Dialogue System
• Long-term Memory

Research Assistant

• Bioinformatics-Gene Analysis.

Visiting Researcher

• Sentiment Classification

Intern

• Software Refactoring

Human-like Memory Integration for Dialogue System

• Designed LLM-based RAG memory architecture for dialogue system.

Multi-modal Summarization System

• Developed audio-image-text fusion summarizer with LLMs.

Dialogue Memory Patent (Huawei)

• Co-inventor of memory storage & retrieval system.

• Overseas Research Attachment Programme (ORAP), CUHK

• ACL-SIGHAN Best Paper Award

• Excellent Scholarship, Southeast University

• 1st Place, Jiangsu Postgraduate Mathematical Modeling Contest

• 1st Place, Chinese Undergraduate Computer Design Contest
• Meritorious Winner, Mathematical Contest in Modeling (MCM)

Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions

• arXiv. A comprehensive survey on memory in AI.

Bridging the Long-Term Gap: A Memory-Active Policy for Multi-Session Task-Oriented Dialogue

• ARR. Novel memory-active policy for task-oriented dialogue.

TWiNS: An Implicit Noise Suppression Approach for Multi-Turn Dialogue Fine-Tuning

• ARR. Proposes turn-weighted noise suppression.

A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation

• AAAI. Multi-modal sticker-based reply system.

PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering

• ACL-SIGHAN. Best Paper.

Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework

• ARR. Fragment-then-compose framework for long-term conversation.

Fine-tuning after Prompting: an Explainable Way for Classification

• ARR. Explainable classification approach.

A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

• ACL 2025 Findings. Multilingual confidence estimation study.

M3SUM: A Novel Unsupervised Language-guided Video Summarization

• ICASSP 2024. Language-guided video summarization.

A Survey of the Evolution of Language Model-Based Dialogue Systems

• Under review. Survey on language model-based dialogue systems.

UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive

• ACL 2023. Unified text-to-text transformer for recommendation.

DPCIPI: A pre-trained deep learning model for predicting cross-immunity between drifted strains of Influenza A/H3N2

• Journal of Automation and Intelligence 2025. Deep learning model for influenza cross-immunity prediction.