Dr. Sun Hui

Biography

I am an LLM Researcher at Sea Group, Shopee LLM Team. I received my Ph.D. in Computer Science from Nankai University, jointly trained with Nanyang Technological University, Singapore, as a member of the Nankai-Baidu Joint Lab (NBJL). I was previously a research intern at Microsoft Research Asia, working on time-series LLMs. My research interests include Code LLMs & Agents, AI for Data Compression, and High-Performance Computing, with 30 publications at venues including KDD, AAAI, WWW, ACL, CVPR and Bioinformatics. Most of my tools are open-sourced on GitHub. Please feel free to reach out if you are interested in my research.

News

  • 🎤 Invited talk at Asian Transplantation Week (ATW) 2026, Busan, Korea.Upcoming
  • 💼 Joined Sea Group as an LLM Researcher in the Shopee LLM Team, Beijing.
  • 🎉 Two papers are accepted by ACL 2026 (including 1 Oral).
  • 🎉 One paper is accepted by CVPR 2026.
  • 📄 ChatAD (work done at MSRA) is released on arXiv.
  • 💼 Joined Microsoft Research Asia as a research intern.
  • 🎉 PMKLC is accepted by SIGKDD 2025 (Oral).

Publications

  • Framework figure
    OPDArena: Understanding Learning and Forgetting in On-Policy Distillation
    Yuanze Xu, Tianzhu Ye, Hui Sun, Wenhui Wang, Li Dong, Furu Wei
    arXiv 2026Tech Report
  • Framework figure
    REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting
    Xu Zhang, Chang Xu, Hui Sun, Nan Ma, Zijian Zhang, Peng Wang, Wei Wang, Li Zhao
    arXiv 2026Tech Report
  • LLCBench: Benchmarking Lossless Compression of Large Language Models
    Hui Sun, Jiashun Chen, Huidong Ma, Xiantong Luo, Chang Xu, Haonan Xie, Lizheng Zu, Qi Ming, Xiaoguang Liu, Gang Wang, Cheng Zhong, Wentong Cai
    Preprint
  • Framework figure
    ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution
    Hui Sun*, Chang Xu†, Haonan Xie, Hao Li, Yuhao Huang, Chuheng Zhang, Ming Jin, Xiaoguang Liu, Gang Wang, Jiang Bian
    arXiv 2026Tech Report
  • Framework figure
    AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent
    Hui Sun†, Yanfeng Ding†, Huidong Ma, Chang Xu, Keyan Jin, Lizheng Zu, Cheng Zhong, Xiaoguang Liu*, Gang Wang*, Wentong Cai
    ACL 2026CCF-A
  • Framework figure
    Efficient Learned Data Compression via Dual-Stream Feature Decoupling
    Huidong Ma, Xinyan Shi, Hui Sun, Xiaofei Yue, Xiaoguang Liu*, Gang Wang*, Wentong Cai
    ACL 2026OralCCF-A
  • Framework figure
    Learned Image Compression via Sparse Attention and Adaptive Frequency
    Huidong Ma, Xinyan Shi, Hui Sun*, Xiaofei Yue, Xiaoguang Liu*, Gang Wang*, Wentong Cai
    CVPR 2026CCF-A
  • Geometric Structure-Aware Diffusion Model with Self-Optimization Strategy for Molecular Generation
    Wenfeng Du, Chunyan Tang, Guanghong Liu, Hui Sun, Jinxiong Zhang, Cheng Zhong
    JCTC 2026
  • End-to-End Story Visualization Framework with Penalty-Based Evaluation using Vision-Language Models
    Lizheng Zu, Yaoqing Jin, Siyi Cao, Shiwei Suo, Haoxin Lyu, Song Fu, Hui Sun, Hao Zhang
    ICASSP 2026CCF-B
  • Artificial Intelligence-Driven Non-Targeted Screening: Applications and Prospects in Environmental and Food Sciences
    Qingrun Liu, Paibin Zhu, Hui Sun, Zhe Chen, Bing Shao
    TIFS 2026
  • Framework figure
    PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database
    Hui Sun, Yanfeng Ding, Liping Yi, Huidong Ma, Gang Wang*, Xiaoguang Liu*, Cheng Zhong, Wentong Cai
    SIGKDD 2025OralCCF-A
  • Framework figure
    Genomics Data Lossless Compression with (s,k)-mer Encoding and Deep Neural Networks
    Hui Sun†, Liping Yi†, Huidong Ma, Yongxia Sun, Yingfeng Zheng, Wenwen Cui, Meng Yan, Gang Wang*, Xiaoguang Liu*
    AAAI 2025CCF-A
  • Framework figure
    MSDZip: Universal Lossless Compression for Multi-source Data via Stepwise-parallel and Learning-based Prediction
    Huidong Ma†, Hui Sun†, Liping Yi, Yanfeng Ding, Xiaoguang Liu*, Gang Wang*
    WWW 2025CCF-A
  • Adaptive Lossless Compression for Genomics Data by Multiple (s,k)-mer Encoding and xLSTM
    Hui Sun†, Yanfeng Ding†, Liping Yi, Huidong Ma, Haonan Xie, Gang Wang*, Xiaoguang Liu*
    ICASSP 2025CCF-B
  • Multi-source Data Lossless Compression via Parallel Expansion Mapping and xLSTM
    Huidong Ma, Hui Sun, Liping Yi, Gang Wang*, Xiaoguang Liu*
    ICASSP 2025CCF-B
  • Framework figure
    PQSDC: A Parallel Lossless Compressor for Quality Scores Data via Sequences Partition and Run-Length Prediction Mapping
    Hui Sun, Yingfeng Zheng, Haonan Xie, Huidong Ma, Cheng Zhong, Meng Yan*, Xiaoguang Liu, Gang Wang
    Bioinformatics 2024CCF-AJCR Q1
  • A Survey and Benchmark Evaluation for Neural-Network-Based Lossless Universal Compressors Toward Multi-Source Data
    Hui Sun†, Huidong Ma†, Feng Ling, Haonan Xie, Yongxia Sun, Liping Yi, Meng Yan*, Cheng Zhong, Xiaoguang Liu, Gang Wang*
    FCS 2025CCF-BJCR Q1
  • LRCB: A Comprehensive Benchmark Evaluation of Reference-free Lossless Compression Tools for Genomics Sequencing Long Reads Data
    Hui Sun†, Huidong Ma†, Yingfeng Zheng, Haonan Xie, Cheng Zhong, Xiaoguang Liu*, Gang Wang*
    DCC 2024CCF-B
  • 融合聚类和卷积神经网络的原理图美观度评价算法
    孙辉, 丁延锋, 王刚*, 李桢荣
    华中科技大学学报 2024EI
  • Framework figure
    高错误率长序列基因组数据敏感序列识别并行算法
    钟诚, 孙辉*
    通信学报 2023CCF-A(中文)
  • SR2C: A Structurally Redundant Short Reads Collapser for Optimizing DNA Data Compression
    Hui Sun†, Huidong Ma†, Yingfeng Zheng†, Haonan Xie, Xiaofei Wang, Xiaoguang Liu*, Gang Wang*
    ICPADS 2023CCF-C
  • PMFFRC: A Large-Scale Genomic Short Reads Compression Optimizer via Memory Modeling and Redundant Clustering
    Hui Sun, Yingfeng Zheng, Haonan Xie, Huidong Ma, Xiaoguang Liu*, Gang Wang*
    BMC Bioinformatics 2023CCF-CJCR Q1
  • 融合过滤和相似度计算的高错误率基因组数据敏感序列识别
    孙辉, 钟诚*
    小型微型计算机系统 2022CCF-B(中文)
  • Prosumer Full Lifecycle Sustainable Footprint Painting for Circular Economy and Community-based Virtual Power Plant: A Multi-objective Optimization Research
    Haonan Xie, Hui Sun, Huan Liu, Tingting He, Hui Hwang Goh, Dongdong Zhang, Wei Dai, Tonni Agustiono Kurniawan, Shen Yuong Wong, Yee Wai Sim
    PSEP 2025
  • Eco-Energetical Analysis of Circular Economy and Community-based Virtual Power Plants (CE-cVPP)
    Haonan Xie, Hui Hwang Goh*, Dongdong Zhang*, Hui Sun, et al.
    Applied Energy 2024JCR Q1
  • The Integration of Supercritical and Reheating Rankine Cycles in Advanced Thermal Energy Systems for Extreme Weather Adaptation
    Haonan Xie, Hui Sun, Dongdong Zhang, Shen Yuong Wong, Hui Hwang Goh
    ICAE 2024
  • ricME: Long-Read Based Mobile Element Variant Detection Using Sequence Realignment and Identity Calculation
    Huidong Ma, Cheng Zhong*, Hui Sun, Danyang Chen, Haixiang Lin
    ISBRA 2023CCF-C
  • Wireless Energy: Paving the Way for Smart Cities and a Greener Future
    Haonan Xie, Renhao Huang, Hui Sun, et al., Dongdong Zhang*, Hui Hwang Goh*
    Energy and Buildings 2023JCR Q1
  • 多维度评价科技工作责任主体信用模型与算法
    唐印浒, 刘峻*, 王淋, 孙辉, 赵凤娇, 钟诚
    广西大学学报 2021CSCD
  • COVID-19 Epidemic Situation, the Outbreak Peak and Cycle Centered on China's No-Drug Control Actions: A Modeling Study
    Haonan Xie, Hui Sun, Wei Dai, Hui Hwang Goh, Dongdong Zhang, Feng Shuang, Thomas Wu, Xianhao Fan
    SSRN 2020

† equal contribution · * corresponding author

Invited Talks

The Next Era of Medicine: AI-Driven Transformation
Invited Speaker · Asian Transplantation Week (ATW) 2026 & Transplantation Science Symposium (TSS) in Asia 2026
TSS Concurrent Symposium 7 (Kidney) — Foundation Models and Clinical Intelligence in Transplantation
Nov 14, 2026 · BEXCO, Busan, Korea

Professional Activities

Reviewer for Conferences

  • AAAI Conference on Artificial Intelligence (AAAI), 2024, 2025, 2026
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), 2025, 2026
  • The Web Conference (WWW), 2025
  • IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
  • International Joint Conference on Neural Networks (IJCNN), 2025

Honors & Awards

Competitions

  • 2025 · Computer Achievement Award, Guangxi Zhuang Autonomous Region — Second Prize
  • 2024 · 11th National Parallel Application Challenge, Team Leader — National Second Prize (Top-2 in China)
  • 2024 · Tianjin "Challenge Cup" Innovation and Entrepreneurship Plan, Technical Director — Gold Prize (Top-1 in Tianjin)
  • 2024 · Nankai University "President's Cup" Innovation and Entrepreneurship Competition, Technical Director — First Prize
  • 2023 · "Huawei Cup" National College Student Storage Modeling Competition — Second Prize (Top-2 in China)
  • 2020 · 8th National Parallel Application Challenge "Intel Cup" — Parallel Fund Award (Top-9 in China)
  • 2020 · Guangxi College Student Computer Design Competition — Third Prize
  • 2019 · Guangxi Computer Society Conference — First Prize, Outstanding Paper
  • 2017 · "Data Creation Cup" National Mathematical Modeling Challenge — First Prize

Scholarships

  • 2024–25 · First Prize Doctoral Graduate Scholarship, Nankai University
  • 2022–24 · Doctoral Graduate "GongNeng" Scholarship, Nankai University (twice)
  • 2021–22 · Outstanding Graduate Student; Annual Outstanding Student Scholarship, Guangxi University
  • 2020–22 · First Prize Graduate Academic Scholarship, Guangxi University (twice)
  • 2019–20 · Outstanding Graduate Cadre, Guangxi University
  • 2017–18 · National Inspirational Scholarship of China

Patents & Software Copyrights

  • A Heuristic Layout and Routing Method for Circuit Schematic Diagrams · CN117057302A · 2nd
  • Method for Evaluating the Aesthetics Level of Circuit Layout, Routing, and Schematic Diagram · CN117058096A · 2nd
  • A Parallel Optimization Method for High-Throughput Genomics Sequencing Reads Data Compression · CN117059181A · 2nd
  • A Parallel Compression Method for High-Throughput Genomic Sequencing Quality Score Data · CN117133365A · 2nd
  • A Non-Intrusive Identification Method for Multi-Parameter Identification of Electromagnetic Equipment Based on Ensemble Algorithms · CN113723495A · 3rd
  • Software copyrights: Research Integrity Evaluation Software System (2nd), DNA Sensitive Sequence Filtering Software (1st), Improved RC4 Cryptography Auxiliary Teaching Platform (1st)
© 2026 Sun Hui · Last updated Oct 2026