Biography
I am currently a Ph.D. student at the School of Artificial Intelligence in Nanjing University , and a member of LAMDA Group , which is led by Prof. Zhi-Hua Zhou (周志华) , and I am supervised by Prof. Ming Li (黎铭) .
I received my B.Sc. from Jilin University in 2019, and my M.Sc. from Nanjing University in 2022. Before starting my Ph.D., I worked as a full-time algorithm engineer at Shopee for over one year, and then returned to Nanjing University for full-time Ph.D. study.
My research interests include large language models (LLMs), machine learning, and information retrieval, with related industry experience at Shopee , ByteDance, and Alibaba.
Research Interests
My recent research focuses on the following areas:
Multimodal & Code LLMs
Search & Recommender
Publications
Preprints & Under Review
Ovis2.5 Technical Report
Ovis Team (Contributor: ), Alibaba Group
2025. Technical Report, arXiv: 2508.11737
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
†, Yun-Ji Zhang† (†Equal Contribution), Zheng Xie, Ren-Biao Liu, Yali Du, Xin-Ye Li, and Ming Li
2026. Preprint, arXiv: 2604.03922
Design-Specification Tiling for ICL-based CAD Code Generation
Yali Du, Sanzhuo Xi, , and Ming Li
2026. Preprint, arXiv: 2603.12712
Loading...
Xin-Ye Li, Ren-Biao Liu, Yun-Ji Zhang, , Zheng Xie, and Ming Li
Loading...
Ren-Biao Liu, Xin-Ye Li, , Yali Du, Jiang-Tian Xue, Ming Li
Loading...
Xin-Ye Li, Yali Du, , and Ming Li
Journal Papers
Mitigating Negative Transfer via Reducing Environmental Disagreement
, Zheng Xie, Hao-Yuan He, and Ming Li
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation
Yali Du†, , and Ming Li
IEEE Transactions on Software Engineering, 2025
This work has been selected for presentation at the ACM International Conference on the Foundations of Software Engineering (FSE), 2026 through the Journal First Track, which invites recently published high-quality journal articles to be presented at the conference.
Learning Personalizable Clustered Embedding for Recommender Systems
Yizhou Chen, Guangda Huzhang, Anxiang Zeng, Qingtao Yu, , Heng-Yi Li, Jingyi Li, Yabo Ni, Han Yu, and Zhiming Zhou
ACM Transactions on Recommender Systems, 2024
Enhancing Unsupervised Domain Adaptation by Exploiting the Conceptual Consistency of Multiple Self-supervised Tasks
, and Ming Li
SCIENCE CHINA Information Sciences, 2023, 66: 142101
Conference Papers
OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender
Zhaoqi Zhang, Haplei Pei, Jun Guo, Tianyu Wang, Yufei Feng, , Shaowei Liu, Aixin Sun
The ACM Web Conference, 2026
Dynamic-Static Synergistic Selection Method for Candidate Code Solutions with Generated Test Cases
Ren-Biao Liu, Jiang-Tian Xue, Chao-Zeng Ma, , Xin-Ye Li, and Ming Li
The 40th AAAI Conference on Artificial Intelligence, 2026
ARBench: Algorithmic Reasoner or API Alchemist? Evaluating Code-Generating LLMs beyond API Calls.
Ren-Biao Liu, Chao-Zeng Ma, An-Qi Li, , Xin-Ye Li, and Ming Li
The 40th AAAI Conference on Artificial Intelligence, 2026
MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs
, Shiyin Lu, Huanyu Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Ming Li
IEEE/CVF International Conference on Computer Vision, 2025
Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?
Ren-Biao Liu, An-Qi Li, Chao-Ding Yang, , and Ming Li
The 42nd International Conference on Machine Learning, 2025
A Joint Learning Model with Variational Interaction for Multilingual Program Translation
Yali Du, , and Ming Li
IEEE/ACM 46th International Conference on Automated Software Engineering, 2024
Ambiguity-Aware Abductive Learning
Hao-Yuan He, , Zheng Xie, and Ming Li
The 41st International Conference on Machine Learning, 2024
Cooperative and Adversarial Learning: Co-Enhancing Discriminability and Transferability in Domain Adaptation
, Zheng Xie, Xin-Ye Li, and Ming Li
The 37th AAAI Conference on Artificial Intelligence, 2023
Semi-Supervised Learning with Support Isolation by Small-Paced Self-Training
Zheng Xie, , and Ming Li
The 37th AAAI Conference on Artificial Intelligence, 2023
Clustered Embedding Learning for Recommender Systems
Yizhou Chen, Guangda Huzhang, Anxiang Zeng, Qingtao Yu, , Heng-Yi Li, Jingyi Li, Yabo Ni, Han Yu, and Zhiming Zhou
The World Wide Web Conference, 2023
Patents
一种面向环境变化的无监督迁移学习图像分类算法
Ming Li (黎铭), , Zhi-Hua Zhou (周志华)
Patent No. 202210461879.4
Awards & Honors
ByteDance Soaring Star Talent Program
筋斗云人才计划
ByteDance · 2025
Value Star Awards
Top 4% (8 out of 200+)
Shopee · Dec 2022
Artificial Intelligence Scholarship
50 recipients across 9 AI-related schools
Nanjing University · 2019
China Collegiate Computing Contest (CCCC)
Outstanding Winner (Highest Honor)
Jilin Province · Mar 2018
ACM-ICPC Asia Regional Contest
Silver Medal
Nanning · Dec 2017
ACM-ICPC Asia EC-Final
Bronze Medal
Shanghai · Dec 2017
Northeast Collegiate Programming Contest
First Prize
Changchun · May 2017
Jilin Province Collegiate Programming Contest
First Prize
Jilin Province · 2017
Work Experience
I have 4.5+ years of industry experience in algorithm R&D across recommendation systems and multimodal foundation models, with work at ByteDance, Alibaba, and Shopee. My experience focuses on building and iterating production systems for ranking, retrieval, and large-scale model applications, with an emphasis on measurable online impact.
ByteDance - TikTok Shop Rec.
Recommendation LLM Algorithm Intern | Soaring Star Talent Program (筋斗云人才计划)
Focused on scaling up TikTok Shop recommendation models for both fine-ranking and retrieval. Core work included unifying the fine-ranking architecture with a decoder-only transformer and independently designing and deploying a generative recall solution that delivered clear offline and online gains.
GMV/u
E-commerce Overall
GMV/u
TikTok Shop Overall
GMV/u
Mall Overall
GMV/u
Mall Feeds
Co-author
OneTrans
HitRate@100
Offline Metric
PV CVR
A/B Testing
PV CTCVR
A/B Testing
GPM
A/B Testing
Alibaba AIDC - Ovis Team
Multimodal LLM Research Intern | Ovis Team
Early core contributor to the Ovis series, deeply involved in the iteration from V1.6 to V2.5. Led the build-out of multi-image and video understanding capabilities from 0 to 1, proposed the MDP3 method for stronger multi-image and long-video understanding, and contributed to GUI Agent SFT and web trajectory data automation.
Ovis 2.5
<40B
Ovis 2.0
OpenCompass
MDP3
First-author
Ovis2.5
Contributor
Downloads
HuggingFace
Likes
HuggingFace
GitHub Stars
Ovis Repo
Related Links
Shopee (Sea Limited)
Core Search Algorithm Engineer (Full-time) | E-commerce Search Ranking
Led the refactoring of Shopee's core search fine-ranking training and serving framework, maintained online models across all sites, and helped extend the refactored design to recall, coarse-ranking, and long-tail teams through modular configuration, pretrained parameter reuse, and user-side computation reuse.
Convergence Data
Module-wise Reuse
Offline Training
37→76 samples/(c·s)
Online Inference
95.5ms→28.8ms
CEL Runtime
Real-world Deployment
PLE
CTR AUC
AutoDis
CTR/CVR AUC
CEL
CTR AUC
CEL [C]
Co-author
CEL [J]
Co-author
AliExpress (Alibaba Group)
Recommendation Algorithm Intern | Fine-Ranking
Worked on multi-objective fine-ranking and country-specific modeling for AliExpress recommendation. Reproduced 14 frontier recommendation papers and completed algorithmic improvements that significantly lifted both CTR and L2P performance in AUC and GAUC.
CTR
AUC
L2P
AUC
CTR
GAUC
L2P
GAUC
ByteDance
Search Algorithm Intern | Vertical Search End-to-End
Worked on end-to-end engineering and algorithm optimization for account vertical search and general search cards in Toutiao apps. Rewrote the Elasticsearch-based recall pipeline and introduced the first GBDT ranking model for Toutiao account search, leading to clear online metric gains.
Query CTR
Vertical Search
Recall Rate
General Search
Top 3 CTR
General Search
Education
Ph.D. in Computer Science and Technology, School of Artificial Intelligence
LAMDA Group · Supervisor: Prof. Ming Li (黎铭)
M.Sc. in Computer Science and Technology, School of Artificial Intelligence
Recommended admission to the LAMDA Group (without entrance examination); ranked 1st in the interview coding test.
B.Sc. in Software Engineering (Excellent Engineer Program)
GPA: 3.7/4.0 (Top 5%); ITMO University Exchange (2017)