😎 About Me

I am Chengyou Jia (贾成铕), a Ph.D candidate in Xi’an Jiaotong University, major in Computer Science, under the supervision of Prof. Minnan Luo. I am also working closely with Prof. Xiaojun Chang. I am currently a visiting student in Singapore under the supervision of Prof. Ivor. Previously, I was a research intern at Shanghai AI LAB, supervised by Dr. Zhiyong Wu. Before starting my doctoral studies, I received my B.E. degree from Xi’an Jiaotong University in 2021.

I have authored several publications in top-tier conferences and journals, including CVPR, AAAI, ACL, ACM-MM, IEEE TIP, among others. I also serve as a reviewer for esteemed conferences and journals like NIPS, ECCV, AAAI, IEEE TIP and IEEE TNNLS.

I am currently on the job market for Fall 2025. Please feel free to reach out!🔥

Research Interests

I am working in the field of CV & Multi-modal. My current research interests and past experience can be summarized as follows:

• Controllable Image Generation: Text-to-image; Layout-to-image; Consistent Generation
• Multimodal learning: Multimodal for Open-set Recognition; Multimodal for Automated Agents
• Object Detection & Identification: Person Search, Person Re-Identification

🔥 News

• 2025.06:   Our papers [T2IS, DenseDiT, AutoGPS] are recently released. 🎉🎉
• 2025.05:   Three papers are accepeted by ACL 2025. 🎉🎉
• 2025.02:   ChatGen is accepeted by CVPR 2025. 🎉🎉
• 2025.01:   OS-Atlas is accepeted by ICLR 2025 (Spotlight). 🎉🎉
• 2024.12:   One paper is accepted by IEEE TCSVT. 🎉🎉
• 2024.11:   Our papers [ChatGen, OS-Atlas, AgentStore, OS-Genesis] are recently released. 🎉🎉
• 2024.10:   Ended a fulfilling internship at Shanghai AI Lab and started as a visiting student in Singapore.
• 2024.07:   One paper is accepted by ACM-MM 2024. See you in Melbourne, Australia. 🎉🎉
• 2023.11:   Two papers are accepted by AAAI 2024. 🎉🎉
• 2023.09:   One paper is accepted by IEEE TIP. 🎉🎉

📖 Educations

• 2021.09 - 2026.06 (expected), M.S. + Ph.D Student, Computer Science, Xi’an Jiaotong University.  
• 2017.09 - 2021.06, B.S. in Computer Science, Xi’an Jiaotong University.

💻 Internships

• 2024.11 - Present, Research Intern @ CFAR, A*STAR. Focus on Multimodal Agents for Image Generation.
• 2024.03 - 2024.10, Research Intern @ Shanghai AI LAB. Focus on Multimodal Agents for OS (Operating System).
• 2022.12 - 2024.03, Research Intern @ SGIT AI Lab, State Grid Corporation of China. Focus on Controllable Image Generation.

📝 Selected Publications

Preprint

Why Settle for One? Text-to-ImageSet Generation and Evaluation 🔥 [Preprint]
Chengyou Jia, Xin Shen, Zhuohang Dang, Changliang Xia, Weijia Wu, Xinyu Zhang, Huangwei Qian, Ivor Tsang, Minnan Luo

(* means equal contributions)

Project Page   (Stay tuned for the code and dataset!)

Preprint

From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios 🔥 [Preprint]
Changliang Xia*, Chengyou Jia*, Zhuohang Dang, Minnan Luo

(* means equal contributions)

Code   Project Page   Models   Datasets  

CVPR 2025

ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting 🔥🔥 [CCF-A]
Chengyou Jia*, Changliang Xia*, Zhuohang Dang, Weijia Wu, Hangwei Qian, Minnan Luo

(* means equal contributions)

Code   Project Page   Datasets   Models  

ACL 2025 Findings

AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant 🔥🔥
Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong Wu

Code   Project Page  

ICLR 2025

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents 🔥🔥 [CAAI-A]
Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, Yu Qiao

Code   Project Page   Demo  

ACM-MM 2024

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition [CCF-A]

Chengyou Jia, Minnan Luo, Xiaojun Chang, Zhuohang Dang, Mingfei Han, Mengmeng Wang, Guang Dai, Sizhe Dang, Jingdong Wang

AAAI 2024

SSMG: Spatial-semantic map guided diffusion model for free-form layout-to-image generation [CCF-A]

Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Mengmeng Wang, Jingdong Wang

IEEE TIP

Collaborative Contrastive Refining for Weakly Supervised Person Search [CCF-A]

Chengyou Jia, Minnan Luo, Caixia Yan, Linchao Zhu, Xiaojun Chang, Qinghua Zheng

🧑‍ Other Paper

• Preprint Autogps: Automated geometry problem solving via multimodal formalization and deductive reasoning
  Bowen Ping, Minnan Luo, Zhuohang Dang, Chenxi Wang, Chengyou Jia

• Preprint Multi-Modal Dataset Distillation in the Wild
  Zhuohang Dang, Minnan Luo, Chengyou Jia, Hangwei Qian, Xiaojun Chang, Ivor W Tsang

• ACL 2025 PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning [CCF-A]
  Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Lingling Zhang, Jun Liu

• ACL 2025 OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis [CCF-A]
  Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu,
  Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

• IEEE TCSVT PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement [CCF-B]
  Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Jingdong Wang, Qinghua Zheng

• ICASSP 2023 Towards Real-time Person Search with Invariant Feature Learning [CCF-B]
  Chengyou Jia, Minnan Luo, Zhuohang Dang, Xiaojun Chang, Qinghua Zheng

• AAAI 2024 Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [CCF-A]
  Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Xiaojun Chang, Jingdong Wang

• IEEE TCSVT Disentangled representation learning with transmitted information bottleneck [CCF-B]
  Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang

• IEEE TIP Disentangled Generation with Information Bottleneck for Enhanced Few-Shot Learning [CCF-A]
  Zhuohang Dang, Minnan Luo, Jihong Wang, Chengyou Jia, Caixia Yan, Guang Dai, Xiaojun Chang, Qinghua Zheng

• IEEE TCSVT Counterfactual Generation Framework for Few-Shot Learning [CCF-B]
  Zhuohang Dang, Minnan Luo, Chengyou Jia, Caixia Yan, Xiaojun Chang, Qinghua Zheng

• IEEE TIP Disentangled Noisy Correspondence Learning
  Zhuohang Dang, Minnan Luo, Jihong Wang, Chengyou Jia, Haochen Han, Herun Wan, Guang Dai, Xiaojun Chang, Jingdong Wang

🎖 Honors and Awards

Honors

• Oct.2022   Outstanding Graduate Student of Xi’an Jiaotong University, Award.
• Jun.2021   Excellent bachelor degree thesis award (Top 1%), Award.
• Jun.2021   Outstanding Graduate Student of Xi’an Jiaotong University, Award.
• Sep.2019   Outstanding Student in Xi’an Jiaotong University
• Sep.2018   Outstanding Student in Xi’an Jiaotong University

Competition Awards

• Jun.2021   Top 1% in the TianChi Global Video Cloud Innovation Challenge, Video Object Segmentation Algorithm Challenge (8/2904).

🎖 Scholarships

• 2023.09   Freshman First Prize Scholarship (PhD)
• 2022.09   First-Class Fellowships for Graduate Students at Xi’an Jiaotong University, Fellowships.
• 2020.09   Computer Science Special Scholarship at Xi’an Jiaotong University, Fellowships.

💬 Academic Services

• Reviewer: NIPS, ECCV, AAAI, ICASSP, IEEE TIP, IEEE TCSVT and IEEE TNNLS.