Yue Wang

王樾

MAI-UI Team Lead, Tongyi Lab, Alibaba Group

Creator of CodeT5 | CodeT5+ | CodeRL | Yi-Coder

Project Lead of Qwen-UI-Agent | MAI-UI | MobileWorld

Singapore

About Me

I am a Staff Algorithm Expert at Tongyi Lab, Alibaba, where I lead the MAI-UI team within the group of Prof. Steven Hoi, focusing on GUI agents. Our research pushes the frontier of digital interaction agents, with key contributions including foundation GUI agent models such as MAI-UI and Qwen-UI-Agent, as well as mobile online benchmark such as MobileWorld. 🔥 I am currently hiring Full-time Researchers/Engineers and Interns to join our team in Hangzhou, Beijing, and Singapore. If you have deep expertise in GUI agents, Agentic RL, LLMs or Coding/work Agents, please feel free to reach out!

Previously, I was a Staff Research Scientist at 01.AI, where my work spanned the entire pipeline of pretraining and post‑training, with a focus on enhancing the coding and reasoning capabilities of Yi models. I led the Yi Coder project and oversaw the multimodal post‑training of Aria. Prior to that, I was a Senior Research Scientist at Salesforce AI Research for three years, where I led or co-led 3 major projects: CodeT5, CodeT5+ and CodeRL. Additionally, I was a core contributor to ApexGuru, an applied project aimed at optimizing code efficiency of Salesforce Apex code.

I obtained my Ph.D. degree at The Chinese University of Hong Kong under the supervision of Prof. Michael R. Lyu and Prof. Irwin King in 2020 and received my B.Sci. from Sun Yat-sen University with an outstanding graduate honor in 2016. I interned at Microsoft Research Asia, Tencent AI, Amazon AWS AI, and Salesforce AI Research. My research interest focuses on code LLMs, multimodal LLMs, and GUI agents.

Publications

🔥[Technical Report'26] Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Hanzhang Zhou∗, Panrong Tong∗, Xu Zhang∗, Quyu Kong, Chenglin Cai, Tianyu Xia, Gongjie Zhang, Jianan Zhang, Long Li, Long Chen, Lei Wang, Gaole Dai, Pengxiang Li, Liangyu Chen, Yue Wang†, Steven Hoi. (* indicates project co-leader, † indicates project leader)

[paper] [code] [website]
[EMNLP 2026] One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding

Chen Liu, Ling Chen, Hanzhang Zhou*, Liangyu Chen, Chenglin Cai, Xin Yu, Steven Hoi, Yue Wang*. (* indicates corresponding author)

[paper]
[Arxiv 2026] What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States

Chen Liu, Ling Chen, Hanzhang Zhou*, Xu Zhang, Quyu Kong, Panrong Tong, Wenhao Wang, Xin Yu, Steven Hoi, Yue Wang*. (* indicates corresponding author)

[paper]
🔥[Technical Report'25] MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Hanzhang Zhou, Xu Zhang, Panrong Tong, Jianan Zhang, Liangyu Chen, Quyu Kong, Chenglin Cai, Chen Liu, Yue Wang*, Jingren Zhou, Steven Hoi. (* indicates project lead)

[paper] [code] [website]
🔥[ACL 2026] MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments

Quyu Kong, Xu Zhang, Zhenyu Yang, Nolan Gao, Chen Liu, Panrong Tong, Chenglin Cai, Hanzhang Zhou, Jianan Zhang, Liangyu Chen, Zhidan Liu, Steven Hoi, Yue Wang.

[paper] [code] [website]
[ICLR 2026] UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning

Liangyu Chen, Hanzhang Zhou, Chenglin Cai, Jianan Zhang, Panrong Tong, Quyu Kong, Xu Zhang, Chen Liu, Yuqi Liu, Wenxuan Wang, Yue Wang*, Qin Jin*, Steven Hoi. (* indicates corresponding author)

[paper] [code]
[ACL'25] Aria-UI: Visual Grounding for GUI Instructions.

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Junnan Li.

[paper] [code] [blog] [media]
[TOSEM'25] HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks.

Fengji Zhang, Linquan Wu, Huiyu Bai, Guancheng Lin, Xiao Li, Xiao Yu, Yue Wang, Bei Chen, Jacky Keung.

[paper] [blog]
[Technical Report'24] ARIA : An Open Multimodal Native Mixture-of-Experts Model.

Dongxu Li, Yudong Liu, Haoning Wu, Yue Wang, Zhiqi Shen, Bowen Qu, Xinyao Niu, Guoyin Wang, Bei Chen, Junnan Li.

[paper] [code] [media]
[Preprint'24] AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions.

Ziming Li, Qianbo Zang, David Ma, Jiawei Guo, Tuney Zheng, Minghao Liu, Xinyao Niu, Yue Wang, Jian Yang, Jiaheng Liu, Wanjun Zhong, Wangchunshu Zhou, Wenhao Huang, Ge Zhang.

[paper] [code]
[Technical Blog'24] Meet Yi-Coder: A Small but Mighty LLM for Code.

01.AI (Tech lead: Yue Wang).

[blog] [code] [media]
[Technical Report'24] Yi: Open Foundation Models by 01.AI.

01.AI

[paper] [code]
[Preprint'24] CodeEditorBench: Evaluating Code Editing Capability of Large Language Models.

Jiawei Guo, Ziming Li, Xueling Liu, Kaijing Ma, Tianyu Zheng, Zhouliang Yu, Ding Pan, Yizhi LI, Ruibo Liu, Yue Wang, Shuyue Guo, Xingwei Qu, Xiang Yue, Ge Zhang, Wenhu Chen, Jie Fu.

[paper] [code]
[EMNLP'23] CodeT5+: Open Code Large Language Models for Code Understanding and Generation.

Yue Wang*, Hung Le*, Akhilesh Deepak Gotmare, Nghi D.Q. Bui, Junnan Li, Steven Hoi. (* indicates equal contribution)

[paper] [code] [blog] [media]
[EMNLP'23] Towards Low-Resource Automatic Program Repair with Meta-Learning and Pretrained Language Models.

Weishi Wang, Yue Wang*, Steven Hoi, Shafiq Joty. (* indicates corresponding author)

[paper]
[FSE'23] RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair.

Weishi Wang*, Yue Wang*, Shafiq Joty, Steven Hoi. (* indicates equal contribution)

The 2023 Symposium on the Foundations of Software Engineering (FSE 2023, Long Paper).

[paper] [slide]
[arXiv'23] CODETF: One-stop Transformer Library for State-of-the-art Code LLMs.

Nghi D.Q. Bui, Hung Le, Yue Wang, Junnan Li, Akhilesh Deepak Gotmare, Steven Hoi.

[paper] [code]
[NeurIPS'22] CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

Hung Le*, Yue Wang*, Akhilesh Deepak Gotmare, Silvio Savarese, Steven Hoi. (* indicates equal contribution)

The 2022 Conference on Neural Information Processing Systems (NeurIPS 2022, Long Paper).

[paper] [code] [blog] [media]
[EMNLP'22 Findings] Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5

Nghi D. Q. Bui, Yue Wang, Steven Hoi.

The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022 Findings, Long Paper).

[paper]
[EMNLP'21] CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

Yue Wang, Weishi Wang, Shafiq Joty, and Steven C.H. Hoi.

The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021, Long Paper).

[paper] [code] [blog] [media] [slide] [poster]
[NAACL'21] Towards Modeling the Style of Translators in Neural Machine Translation

Yue Wang, Cuong Hoang, and Marcello Federico.

The 2021 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021, Short Paper).

[paper]
[ICASSP'21] Machine Translation Verbosity Control for Automatic Dubbing

Surafel M Lakew, Marcello Federico, Yue Wang, Cuong Hoang, Yogesh Virkar, Roberto Barra-Chicote, Robert Enyedi.

The 2021 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021, Long Paper).

[paper]
[EMNLP'20] VD-BERT: A Unified Vision and Dialog Transformer with BERT

Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, and Steven C.H. Hoi.

The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020, Long Paper).

[paper] [code] [slide] [media] [leaderboard]
[EMNLP'20] Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings

Yue Wang, Jing Li, Michael Lyu and Irwin King.

The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020, Long Paper).

[paper] [code] [video]
[ACL'19] Topic-Aware Neural Keyphrase Generation for Social Media Language

Yue Wang, Jing Li, Hou Pong Chan, Irwin King, Michael R. Lyu, Shuming Shi.

The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019, Long Paper).

[paper] [code] [slide]
[NAACL'19] Microblog Hashtag Generation via Encoding Conversation Contexts

Yue Wang, Jing Li, Irwin King, Michael R. Lyu, Shuming Shi.

The 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019, Long Paper, Oral).

[paper] [code] [slide] [video]
[IJCAI'18] Code Completion with Neural Attention and Pointer Networks

Jian Li, Yue Wang, Michael R. Lyu, Irwin King.

The 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018, Long Paper, Oral).

[paper] [slide]

Working Experience

Mar 2025-Now: Staff Algorithm Expert in Alibaba, Singapore.
Dec 2023-Dec 2024: Staff Research Scientist in 01 AI, Singapore.
Jan 2021-Dec 2023: Senior Research Scientist in Salesforce AI Research, Singapore.

Summer 2020: Applied Scientist Intern at Amazon AWS AI Lab, California, USA. Mentor: Prof. Marcello Federico and Hoang Cuong
Fall 2019: Research Intern at Salesforce AI Research, Singapore. Mentor: Prof. Steven Hoi and Prof. Shafiq Rayhan Joty
Summer 2018: Research Intern at the NLP Center of Tencent AI Lab, Shenzhen. Mentor: Prof. Jing Li
Spring 2016: Research Assistant at the Department of Electrical and Computer Engineering in Brigham Young University, Utah, USA. Advisor: Prof. Brent Nelson
Summer 2015: Research Intern at System Group of Microsoft Research Asia, Beijing. Mentor: Cheng Chen

Selected Awards

Postgraduate Student Scholarship, CUHK, 2016-2020
Outstanding Graduate Student, Sun Yat-sen University, 2016
Third Prize in the 13th Guangdong Collegiate Programming Contest (ACM-ICPC GDCPC), 2015
National Scholarship, Ministry of Education of the P. R. China, 2013

Academic Service

Journal Reviewer: TKDE, TIST, TOSEM
Conference Reviewer: ICML (2024, 2025), ICLR (2024, 2025), NeurIPS (2023), COLM (2024,2025), ACL (2021, 2022, 2025), EMNLP (2019, 2021, 2023)