I am a Staff Researcher at Tencent (青云计划 ‘Project Up’ Talent Programme), where I serve as Research Lead for World Models, Agentic AI, and AIGC for Games. I am also Adjunct Faculty at NUS National University of Singapore (NUS), Department of Electrical and Computer Engineering (ECE).

I earned my PhD degree from NUS ECE, supervised by Prof. Robby T. Tan, and previously interned at Adobe Research, mentored by Prof. Connelly Barnes and Prof. Eli Shechtman. I hold an M.Sc. from NUS ECE and a B.Eng. from the UESTC UESTC.

I have published papers at top international venues including CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR and ACL, with . 📢 I’m hiring self-motivated interns.

📜 Research

Game World Models: Persistent State, Mechanics Consistency, and Controllable Agents
Agentic AI: Coding Agents, Agentic VLMs, and Video Generation
AIGC for Games
Multimodal Learning & VLMs

🔬 Projects

arXiv 2026	H3-World: Turning Language Understanding into World Control Danze Chen^, Zeqing Wang^, Ziyue Lin, Xingyi Yang^†, Yeying Jin^†‡ Project Page arXiv Turns a video generator's own language understanding into grounded character and camera control, at 0.199% params.
arXiv 2026	WorldMind: Decoupled Game World Model for State-Aware NPC Behavior Zhiyang Deng, Boran Zhang, Danze Chen, Yeying Jin^†‡ Project Page arXiv The first decoupled game world model, closing the loop from understanding to generation; preferred in ~70% of comparisons.
arXiv 2026	StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation Zijun Lin, Zeqing Wang, Cheston Tan, Bihan Wen, Yeying Jin^†‡ Project Page arXiv Model Dataset Jointly generates frames and internal game states (health, meters, timers), improving mechanics fidelity by 18.6%.
arXiv 2026	ReactiveGWM: Steering NPC in Reactive Game World Models Zeqing Wang, Danze Chen, Zhaohu Xing, Zizhao Tong, Yinhan Zhang, Xingyi Yang^†, Yeying Jin^†‡ Project Page arXiv Model Dataset NPCs follow high-level strategies (Offense / Defense / Control), transferring zero-shot to unseen games.
arXiv 2026	SCOPE: Scalable World Model via Consistent Prediction Zizhao Tong, Yeying Jin^†‡, Hongfeng Lai, Zeqing Wang, Zhaohu Xing, Kexu Cheng, Haoran Xu, Zhao Pu, Shangwen Zhu, Ruili Feng, Jian Zhao, Yan Zhang, Hao Tang, Ling Shao^† Project Page arXiv Model Dataset Link An interactive FPS world model trained on CrossFPS, the first multi-game FPS dataset: 69K clips, 7 titles, 10-DoF controls.
arXiv 2026	Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models Shangwen Zhu, Qianyu Peng, Zhao Pu, Zhilei Shu, Xiangrui Ke, Zhaohu Xing, Zizhao Tong, Zeqing Wang, Xinyu Cui, Huangji Wang, Jian Zhao, Yeying Jin^‡, Fan Cheng^†, Ruili Feng^† Project Page arXiv Play Model Dataset A natural-language action interface for multi-entity control: 89% cross-entity transfer success vs. 43% for action-ID baselines.
	AI Photobooth AI Photobooth • 2025.12 370+ Generated AI Images in 1 hour · Top 3 Popular 6 Heroes · 2 Styles · 3 Games Demo: Online Generation Video (CN) Video (EN)
	Honor of Kings (HOK) AIUGC Detective & Esports Poster HOK Flowborn Dimensional Editor • 2025.08–Present Shared DIY Poster platform: 22.5K players · 2.1M posters across Portrait, Detective & Esports Battle Loading, In-Game Hero, In-Game Popup One-Click Sharing on HOK Camp, X, Instagram, Facebook Demo: Online Generation Video (CN) Video (EN)
	Honor of Kings (HOK) AIUGC Portrait Poster HOK Flowborn Dimensional Editor • 2025.06–Present Avg. 9 AI posters per player · Thousands+ overseas & domestic mentions 80% In-Game Display · 99% Positive Sentiment Demo: Online Generation Video (CN) Video (EN)
	Honor of Kings (HOK) AIUGC Online Hero Generation HOK Creator Studio • 2024.12–Present 58K Generated AI Images · 22% Save Rate 35K+ Active Users 98 Heroes · 12 Styles · 13s Generation Time Demo: Online Generation Video (CN) Video (EN)
	Honor of Kings (HOK) AIPGC Avatars/Stickers HOK Avatar Center • 2024.07–2024.11 12× Launch · 98 Heroes · 2 Styles · 2 Halloween Topics 600K+ Exposure · 60K Engagements Available on HOK Camp, VK, X, Instagram, Facebook, WhatsApp, Discord, Sticker Demo: Avatar Center Video (CN) Video (EN)

📝 Publications

SIGGRAPH Asia 2026	LatentDance: Towards Realistic and Dynamic Character Animation via Identity-Aware Motion Representation Yixin Yang^, Yeying Jin^, Jiawei Zhang, Long Sun, Xu Cheng^‡, Jinshan Pan^† ACM SIGGRAPH Asia, 2026, Kuala Lumpur, Malaysia Paper \| \| Project Page Warps the reference character's own latents along the skeleton instead of sparse-to-dense pose alignment; best FVD on TikTok.
ACM MM 2026	BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data Wei Zhang, Xin Li, Peishu Shi, Jialin Gao, Xuekang Peng, Zhichao Lian^†, Yeying Jin^†‡ ACM Multimedia (ACM'MM), 2026, Rio, Brazil arXiv \| Project Page Mask-free video try-on learned from image-level pseudo data; released with the OmniView dataset.
	Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Meng Chu^, Xuan Billy Zhang^, Kevin Qinghong Lin^, Lingdong Kong^, Jize Zhang^, Teng Tu^, Weijian Ma^, Ziqi Huang, Senqiao Yang, Wei Huang, Yeying Jin, Zhefan Rao, Jinhui Ye, Xinyu Lin, Xichen Zhang, Qisheng Hu, Shuai Yang, Leyang Shen, Wei Chow, Yifei Dong, Fengyi Wu, Quanyu Long, Bin Xia, Shaozuo Yu, Mingkang Zhu, Wenhu Zhang, Jiehui Huang, Haokun Gui, Haoxuan Che^†, Long Chen^†, Qifeng Chen^†, Wenxuan Zhang^†, Wenya Wang^†, Xiaojuan Qi^†, Yang Deng^†, Yanwei Li^†, Mike Zheng Shou^†, Zhi-Qi Cheng^†, See-Kiong Ng^†, Ziwei Liu^†, Philip Torr^†, Jiaya Jia^† arXiv preprint*, 2026 arXiv \| \| Project Page
ECCV 2026	MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation Yinhan Zhang^, Dingwei Tan^, Xianghao Kong, Yue Ma^‡, Yeying Jin^†, Anyi Rao^† European Conference on Computer Vision (ECCV), 2026, Malmö, Sweden arXiv \|
ICML 2026	CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping Haoyu Zhao, Jiaxi Gu, Haoran Chen, Qingping Zheng, Yeying Jin, Hongyi Yang, Junqi Cheng, Yuang Zhang, Zenghui Lu, Huan Yu, Jie Jiang, Peng Shu, Zuxuan Wu^†, Yu-Gang Jiang^† International Conference on Machine Learning (ICML), 2026, Seoul, South Korea arXiv \| \| Project Page
ACM MM 2026	CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-controllable Video Generation Haoyu Zhao, Zihao Zhang, Jiaxi Gu, Haoran Chen, Qingping Zheng, Pin Tang, Yeying Jin, Yuang Zhang, Junqi Cheng, Zenghui Lu, Peng Shu, Zuxuan Wu^†, Yu-Gang Jiang^† ACM Multimedia (ACM'MM), 2026, Rio, Brazil arXiv \| \| Project Page
	InstanceAnimator: Multi-Instance Sketch Video Colorization Yinhan Zhang^, Yue Ma^, Bingyuan Wang, Kunyu Feng, Yeying Jin^‡, Qifeng Chen, Anyi Rao, Zeyu Wang^† arXiv preprint, 2026 arXiv \|
	Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers Nanxiang Jiang, Zhaoxin Fan^†, Baisen Wang, Daiheng Gao, Junhang Cheng, Jifeng Guo, Yalan Qin, Yeying Jin^‡, Hongwei Zheng, Faguo Wu^†, Wenjun Wu International Conference on Machine Learning (ICML), 2026, Seoul, South Korea arXiv \|
	Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack Nanxiang Jiang, Zhaoxin Fan^†, Enhan Kang, Daiheng Gao, Yun Zhou, Yanxia Chang, Zheng Zhu, Yeying Jin, Wenjun Wu Computer Vision and Pattern Recognition (CVPR) Findings, 2026, Denver, USA arXiv \|
	Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement Xiaoran Sun^, Liyan Wang^, Yeying Jin^‡, Kin-man Lam, Zhixun Su^†, Yang Yang, Jinshan Pan, Cong Wang^‡ Computer Vision and Pattern Recognition (CVPR) Findings, 2026, Denver, USA arXiv \|
ECCV 2026	Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis Chenghao Qian, Nedko Savov, Lingdong Kong, Yeying Jin, Rui Song, Wenjing Li, Zhun Zhong, Jiaqi Ma, Gustav Markkula, Luc Van Gool European Conference on Computer Vision (ECCV), 2026, Malmö, Sweden arXiv \| \| Project Page
	UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment Wei Zhang^, Yeying Jin^, Xin Li, Yan Zhang, Xiaofeng Cong, Cong Wang, Fengcai Qiao, Zhichao Lian^† Association for the Advancement of Artificial Intelligence (AAAI), 2026, Singapore arXiv \| \| bibtex
TCSVT 2025	MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation Siyuan Wang^, Jiawei Liu^, Wei Wang^†, Yeying Jin, Jinsong Du, Zhi Han IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025 arXiv \| \| bibtex
	PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework Sixiang Chen^, Jianyu Lai^, Jialin Gao^, Tian Ye, Haoyu Chen, Hengyu Shi, Shitong Shao, Yunlong Lin, Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, Lei Zhu^† The International Conference on Learning Representations (ICLR)*, 2026, Rio, Brazil arXiv \| \| bibtex \| Project Page \| online demo \| video \| link
	Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attacks Zhiying Li^, Yeying Jin^, Fan Shen, Zhi Liu, Weibin Chen, Pengju Zhang, Xiaomei Zhang, Boyu Chen, Michael Shen, Kejian Wu, Zhaoxin Fan^†, Jin Dong^† Pattern Recognition (PR), 2025 arXiv \| bibtex \| link
	Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy Yinghao Chen, Yeying Jin^†‡, Xiang Chen, Yanyan Wei^†, Ziyang Yan, Yaowen Fu Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv
	GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing Sixiang Chen, Tian Ye, Yunlong Lin, Yeying Jin, Yijun Yang, Haoyu Chen, Jianyu Lai, Song Fei, Zhaohu Xing, Fugee Tsung, Lei Zhu^† International Conference on Computer Vision (ICCV), 2025, Hawaii, USA paper \| bibtex
	DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy Qirui Yang^, Fangpu Zhang^, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue^†, Jingyu Yang^† ACM Multimedia (ACM'MM), 2025, Dublin, Ireland arXiv \| \| bibtex \| Project Page
	JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration Yunlong Lin^, Zixu Lin^, Haoyu Chen^, Panwang Pan^, Chenxin Li, Sixiang Chen, Yeying Jin, Wenbo Li^†, Xinghao Ding^† Computer Vision and Pattern Recognition (CVPR), 2025, Nashville, USA arXiv \| \| bibtex \| Project Page \| online demo \| link
	LoViF 2026: The First Challenge on Weather Removal in Videos Chenghao Qian, Xin Li, Yeying Jin^†, Shangquan Sun, Yilian Zhong, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv
	NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results Xin Li, Yeying Jin^†, Suhang Yao, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv \| \| competition \| challenge
	NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results Xin Li, Yeying Jin^†, Xin Jin, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2025, Nashville, USA arXiv \| \| bibtex \| slides \| video \| competition \| challenge
	Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal Yeying Jin, Xin Li, Jiadong Wang, Yan Zhang, Malu Zhang European Conference on Computer Vision (ECCV), 2024, Milan, Italy arXiv \| \| bibtex \| poster \| slides \| video \| competition \| challenge
	HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models Songtao Jiang, Yan Zhang, Yeying Jin, Zhihang Tang, Yangyang Wu, Yang Feng, Jian Wu, Zuozhu Liu^† Association for Computational Linguistics (ACL), 2025, Vienna, Austria arXiv \| bibtex
	Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering Songtao Jiang^, Chenyi Zhou^, Yan Zhang, Yeying Jin, Zuozhu Liu^† Association for Computational Linguistics (ACL), 2025, Vienna, Austria arXiv \| bibtex
	Modality-Fair Preference Optimization for Trustworthy MLLM Alignment Songtao Jiang, Yan Zhang, Ruizhe Chen, Tianxiang Hu, Yeying Jin, Qinglin He, Yang Feng, Jian Wu, Zuozhu Liu^† International Joint Conference on Artificial Intelligence (IJCAI), 2025, Montreal, Canada arXiv \| bibtex
	Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models Songtao Jiang^, Yan Zhang^, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, Zuozhu Liu^† ADHIP Best Paper Award, 2024, Jiaxing, China arXiv \| \| bibtex
	Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models Songtao Jiang^, Tuo Zheng^, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu^† EMNLP Findings, 2024, Miami, Florida arXiv \| \| bibtex
	Dual-Rain: Video Rain Removal using Assertive and Gentle Teachers Tingting Chen^, Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan European Conference on Computer Vision (ECCV)*, 2024, Milan, Italy paper \| bibtex
	UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt Xin Li^, Bingchen Li^, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren, Zhibo Chen^† European Conference on Computer Vision (ECCV), 2024, Milan, Italy arXiv \| \| bibtex
	NightHaze: Nighttime Image Dehazing via Self-Prior Learning Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2025, Philadelphia, USA arXiv \| \| bibtex \| Project Page
	SeD: Semantic-Aware Discriminator for Image Super-Resolution Bingchen Li^, Xin Li^, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen^† Computer Vision and Pattern Recognition (CVPR), 2024, Seattle, USA arXiv \| \| bibtex
	DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity Yeying Jin, Wei Ye, Wenhan Yang, Yuan Yuan, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada arXiv \| \| bibtex \| paper \| poster \| slides First diffusion-based shadow removal performs robustly on hard, soft and self shadows.
	NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Shunli Zhang, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada arXiv \| bibtex \| poster
	Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression Yeying Jin, Wenhan Yang, Robby T. Tan European Conference on Computer Vision (ECCV), 2022, Tel Aviv, Israel arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video \| data \| link \| online demo Night image enhancement by enhancing low-light regions and suppressing light-effects regions.
	DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network Yeying Jin, Aashish Sharma, Robby T. Tan International Conference on Computer Vision (ICCV), 2021, Montreal, Canada arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video First unsupervised hard and soft shadow removal.
	Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution Yeying Jin^, Beibei Lin^, Wending Yan, Yuan Yuan, Wei Ye, Robby T. Tan ACM Multimedia (ACM'MM), 2023, Ottawa, Canada arXiv \| \| bibtex \| paper \| poster \| slides \| data First learning-based network handling nighttime haze and glow using APSF.
	Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning Yeying Jin, Ruoteng Li, Wenhan Yang, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2023, Washington DC, USA arXiv \| \| bibtex \| paper \| poster \| slides First reflectance layer estimation that performs robustly even in the presence of shadows and specularities.
	Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal Yeying Jin, Wending Yan, Wenhan Yang, Robby T. Tan Asian Conference on Computer Vision (ACCV), 2022, Macau, China arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| data Dense and/or non-uniform fog removal.

💬 Organizer

Workshop	Title	Date & Venue
ECCV 2026 LoViF Workshop	The 2nd Workshop on Low‑Level Vision Frontiers (Generative AI, Preference Optimization, and Agentic Systems)	09.2026 Malmö, Sweden
CVPR 2026 LoViF Workshop	The 1st Workshop on Low‑Level Vision Frontiers (Generative AI, Preference Optimization, and Agentic Systems)	06.04.2026@504 Denver, USA
CVPR 2026 AGENTIC Workshop	Workshop on Agentic AI for Visual Media	06.03.2026@1EF Denver, USA
CVPR 2026 URVIS Workshop	Unified Robotic Vision with Cross-Modal Sensing and Alignment	06.04.2026@4AB Denver, USA
CVPR 2026 AIGENS Workshop	The 3rd Workshop on AI for Content Generation, Quality Enhancement and Streaming	06.03.2026@105 Denver, USA
CVPR 2026 NTIRE Challenge	The 2nd Challenge on Day and Night Raindrop Removal for Dual-Focused Images	06.04.2026@504 Denver, USA
AAAI 2026 Workshop	The Application of Generative AI and Intelligent Agents in Low-level Vision	01.2026 Singapore
CVPR 2025 NTIRE Challenge	The 1st Challenge on Day and Night Raindrop Removal for Dual-Focused Images	06.2025 Nashville, USA

🎤 Invited Talks

Host	Topic	Date & Venue
Runway (invited by Robin Kahlow)	Game World Model	06.26.2026 Singapore
CVPR 机器之心	Invited Talk (w/ Ziwei Liu^NTU, Mike Zheng Shou^NUS, Ruoshi Liu^UMD)	06.06.2026 Denver, USA
CVPR 2026 URVIS (invited by Zongwei Wu)	World Model	06.04.2026 Denver, USA
CVPR 2026 AGENTIC (invited by Jinjin Gu)	Game World Model	06.03.2026 Denver, USA
CVPR 2026 AIGENS (invited by Marcos V. Conde)	Game World Model for Video Generation	06.03.2026 Denver, USA
CVPR 2026 NTIRE (invited by Zongwei Wu)	Game World Model	06.03.2026 Denver, USA
SPARK Share	From Video Generation to World Model	05.22.2026 Singapore
Singapore Vision Day (invited by Gim Hee Lee)	Game World Model World Model Panel Discussion (w/ Qi Wu^{U Adelaide}, Angela Dai^TUM, Xingang Pan^NTU)	05.16.2026 Singapore
ICLR Booth Talk Game Session Talk	From AIGC to World Model	04.25.2026 Rio, Brazil
NUS EE6934 Emerging Topics in AI and Deep Learning Guest Lecture (invited by Xinchao Wang)	From AIGC to World Model	03.17.2026 Singapore
NUS CEG5304 Deep Learning Guest Lecture (invited by Yuecong Xu)	World Model and Agentic Video Generation	11.2026 Singapore
AAAI (invited by Xin Li)	From Creation to Perception: Generative AI for Content Generation	01.2026 Singapore
Low-level Community (invited by Xiang Chen)	AIGC-Powered Game Marketing: From Generation to Deployment	01.2026 Singapore
ICCV AIGENS (invited by Marcos V. Conde)	From Creation to Perception: Generative AI for Content Generation	10.2025 Hawaii, USA
Programmers Video	Exploring SORA: Unlocking the Core of AI Video Creation [Video]	11.2025 Singapore
	AI Video Gen \| When Wukong meets Yayoi Kusama	05.2025 Singapore
ICLR (invited by Kevin QH. Lin)	AI × Gaming: Creative Applications of AIGC [Video]	04.2025 Singapore
	AI Generation: Inspiring Game Marketing and Development	02.2025 Singapore
AI TIME	Raindrop Clarity: Dual-Focused, Day and Night	09.2024
AI TIME	Shadow Removal using Diffusion Model	01.2024
	Applications of Generative AI	11.2023 Singapore
Huawei	Visibility Enhancement using Generative Model	07.2023
Adobe (invited by Eric Kee)	NextCam Reading Group: Light-effects Suppression	07.2023 USA
Huawei	Image/Video Restoration and Generation	03.2023
AI TIME	Intrinsic Image Decomposition	02.2023
(invited by Hanshu Yan)	Diffusion Model in Image Processing	01.2023
Huawei	Visibility Enhancement in Nighttime	12.2022 Singapore
AI TIME	Unsupervised Image Restoration and Generation	11.2022

Presented at	Date & Venue
VALSE	05.2024, Chongqing, China
Singapore Vision Day	05.2023, Singapore
AI Research Symposium	01.2023, Singapore

✍️ Blogs

Title	Date
Google 又放大招：Gemini Omni 和 Gemini 3.5 同日登场，文生视频屠榜	05.2026
一图胜千言！GPT Image 2 联手 HappyOyster 秒出世界模型，再战 Nano Banana 2 谁更能打？	04.2026
一键创世，遥遥领先？快乐生蚝HappyOyster到底有多快乐	04.2026
世界模型再添王炸，Marble 1.1一手测评来了！	04.2026
AI视频的大结局？Seedance 2.0掀桌子了! 下一站在哪?	02.2026
Sora2：视频生成一年半的变化与展望	10.2025
Sora揭秘: OpenAI文生视频模型, Diffusion+Transformer带来的思考	02.2024
AI赋能UGC \| 点亮每一位玩家的英雄梦	2025
CVPR 2025 NTIRE赛事 \| 首届多场景雨滴去除挑战赛	06.2025
ECCV 2022 \| 夜间图像增强: 层分解遇到光效应抑制网络	10.2022

🏫 Education

01.2020-01.2024: Ph.D. (AI and Deep Learning), NUS, Singapore (CAP: 4.75/5.00)
08.2017-08.2018: M.S. (Electrical and Computer Engineering), NUS, Singapore
09.2013-07.2017: B.Eng (Electronic Information Engineering), UESTC, China (GPA: 3.93/4.00)

👔 Internship and Work Experience

11.2023-Present: Staff Researcher and Research Lead for World Models, Agentic AI, and AIGC at IEG Global, Singapore.
06.2023-09.2023: Adobe Research Intern, Creative Intelligence Lab, mentored by Prof. Connelly Barnes, Prof. Eli Shechtman, worked with Yuqian Zhou, Lingzhi Zhang, Sohrab Amirghodsi, Eric Kee.
01.2019-01.2020: Machine Learning Researcher at Singapore, advised by Prof. Jiashi Feng, worked on Biomedical Image Synthesis, Super-resolution, Tumor Segmentation and Classification, expo demo for “Deep Learning-Based End-to-end Automatic Contouring and Automated Radiation Therapy Treatment Planning System”.

🎖 Honors and Awards

“Yayoi Kusama × Wukong”, ModelScope Wan 2.1 Video Generation Challenge — 2nd Place
Knowledge Award, Excellent R&D Award, Outstanding Mentor, Outstanding Contributor
CVPR Student Mentor, Tencent Outstanding Mentor Award
AI Singapore (AISG) Ph.D. Fellowship (Singapore’s most prestigious Ph.D. scholarship) — Theme: Continuous Learning AI, Self-supervised Learning

💻 Professional Services

Journal Reviewer: TPAMI, IJCV, TIP, TNNLS, TMM, TCSVT, TVCJ, NEUCOM, CVIU, etc.
Conference Reviewer: ICML (Gold Reviewer Award), NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, ACM MM, ACL, MICCAI, ACCV, IJCAI, IJCNN, etc.
Teaching Assistant: EE5731 Visual Computing, EE5904 Neural Network (NUS ECE)

SIGGRAPH Asia 2026	LatentDance: Towards Realistic and Dynamic Character Animation via Identity-Aware Motion Representation Yixin Yang^, Yeying Jin^, Jiawei Zhang, Long Sun, Xu Cheng^‡, Jinshan Pan^† ACM SIGGRAPH Asia, 2026, Kuala Lumpur, Malaysia Paper \| \| Project Page Warps the reference character's own latents along the skeleton instead of sparse-to-dense pose alignment; best FVD on TikTok.
ACM MM 2026	BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data Wei Zhang, Xin Li, Peishu Shi, Jialin Gao, Xuekang Peng, Zhichao Lian^†, Yeying Jin^†‡ ACM Multimedia (ACM'MM), 2026, Rio, Brazil arXiv \| Project Page Mask-free video try-on learned from image-level pseudo data; released with the OmniView dataset.
	Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Meng Chu^, Xuan Billy Zhang^, Kevin Qinghong Lin^, Lingdong Kong^, Jize Zhang^, Teng Tu^, Weijian Ma^, Ziqi Huang, Senqiao Yang, Wei Huang, Yeying Jin, Zhefan Rao, Jinhui Ye, Xinyu Lin, Xichen Zhang, Qisheng Hu, Shuai Yang, Leyang Shen, Wei Chow, Yifei Dong, Fengyi Wu, Quanyu Long, Bin Xia, Shaozuo Yu, Mingkang Zhu, Wenhu Zhang, Jiehui Huang, Haokun Gui, Haoxuan Che^†, Long Chen^†, Qifeng Chen^†, Wenxuan Zhang^†, Wenya Wang^†, Xiaojuan Qi^†, Yang Deng^†, Yanwei Li^†, Mike Zheng Shou^†, Zhi-Qi Cheng^†, See-Kiong Ng^†, Ziwei Liu^†, Philip Torr^†, Jiaya Jia^† arXiv preprint*, 2026 arXiv \| \| Project Page
ECCV 2026	MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation Yinhan Zhang^, Dingwei Tan^, Xianghao Kong, Yue Ma^‡, Yeying Jin^†, Anyi Rao^† European Conference on Computer Vision (ECCV), 2026, Malmö, Sweden arXiv \|
ICML 2026	CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping Haoyu Zhao, Jiaxi Gu, Haoran Chen, Qingping Zheng, Yeying Jin, Hongyi Yang, Junqi Cheng, Yuang Zhang, Zenghui Lu, Huan Yu, Jie Jiang, Peng Shu, Zuxuan Wu^†, Yu-Gang Jiang^† International Conference on Machine Learning (ICML), 2026, Seoul, South Korea arXiv \| \| Project Page
ACM MM 2026	CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-controllable Video Generation Haoyu Zhao, Zihao Zhang, Jiaxi Gu, Haoran Chen, Qingping Zheng, Pin Tang, Yeying Jin, Yuang Zhang, Junqi Cheng, Zenghui Lu, Peng Shu, Zuxuan Wu^†, Yu-Gang Jiang^† ACM Multimedia (ACM'MM), 2026, Rio, Brazil arXiv \| \| Project Page
	InstanceAnimator: Multi-Instance Sketch Video Colorization Yinhan Zhang^, Yue Ma^, Bingyuan Wang, Kunyu Feng, Yeying Jin^‡, Qifeng Chen, Anyi Rao, Zeyu Wang^† arXiv preprint, 2026 arXiv \|
	Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers Nanxiang Jiang, Zhaoxin Fan^†, Baisen Wang, Daiheng Gao, Junhang Cheng, Jifeng Guo, Yalan Qin, Yeying Jin^‡, Hongwei Zheng, Faguo Wu^†, Wenjun Wu International Conference on Machine Learning (ICML), 2026, Seoul, South Korea arXiv \|
	Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack Nanxiang Jiang, Zhaoxin Fan^†, Enhan Kang, Daiheng Gao, Yun Zhou, Yanxia Chang, Zheng Zhu, Yeying Jin, Wenjun Wu Computer Vision and Pattern Recognition (CVPR) Findings, 2026, Denver, USA arXiv \|
	Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement Xiaoran Sun^, Liyan Wang^, Yeying Jin^‡, Kin-man Lam, Zhixun Su^†, Yang Yang, Jinshan Pan, Cong Wang^‡ Computer Vision and Pattern Recognition (CVPR) Findings, 2026, Denver, USA arXiv \|
ECCV 2026	Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis Chenghao Qian, Nedko Savov, Lingdong Kong, Yeying Jin, Rui Song, Wenjing Li, Zhun Zhong, Jiaqi Ma, Gustav Markkula, Luc Van Gool European Conference on Computer Vision (ECCV), 2026, Malmö, Sweden arXiv \| \| Project Page
	UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment Wei Zhang^, Yeying Jin^, Xin Li, Yan Zhang, Xiaofeng Cong, Cong Wang, Fengcai Qiao, Zhichao Lian^† Association for the Advancement of Artificial Intelligence (AAAI), 2026, Singapore arXiv \| \| bibtex
TCSVT 2025	MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation Siyuan Wang^, Jiawei Liu^, Wei Wang^†, Yeying Jin, Jinsong Du, Zhi Han IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025 arXiv \| \| bibtex
	PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework Sixiang Chen^, Jianyu Lai^, Jialin Gao^, Tian Ye, Haoyu Chen, Hengyu Shi, Shitong Shao, Yunlong Lin, Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, Lei Zhu^† The International Conference on Learning Representations (ICLR)*, 2026, Rio, Brazil arXiv \| \| bibtex \| Project Page \| online demo \| video \| link
	Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attacks Zhiying Li^, Yeying Jin^, Fan Shen, Zhi Liu, Weibin Chen, Pengju Zhang, Xiaomei Zhang, Boyu Chen, Michael Shen, Kejian Wu, Zhaoxin Fan^†, Jin Dong^† Pattern Recognition (PR), 2025 arXiv \| bibtex \| link
	Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy Yinghao Chen, Yeying Jin^†‡, Xiang Chen, Yanyan Wei^†, Ziyang Yan, Yaowen Fu Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv
	GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing Sixiang Chen, Tian Ye, Yunlong Lin, Yeying Jin, Yijun Yang, Haoyu Chen, Jianyu Lai, Song Fei, Zhaohu Xing, Fugee Tsung, Lei Zhu^† International Conference on Computer Vision (ICCV), 2025, Hawaii, USA paper \| bibtex
	DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy Qirui Yang^, Fangpu Zhang^, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue^†, Jingyu Yang^† ACM Multimedia (ACM'MM), 2025, Dublin, Ireland arXiv \| \| bibtex \| Project Page
	JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration Yunlong Lin^, Zixu Lin^, Haoyu Chen^, Panwang Pan^, Chenxin Li, Sixiang Chen, Yeying Jin, Wenbo Li^†, Xinghao Ding^† Computer Vision and Pattern Recognition (CVPR), 2025, Nashville, USA arXiv \| \| bibtex \| Project Page \| online demo \| link
	LoViF 2026: The First Challenge on Weather Removal in Videos Chenghao Qian, Xin Li, Yeying Jin^†, Shangquan Sun, Yilian Zhong, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv
	NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results Xin Li, Yeying Jin^†, Suhang Yao, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2026, Denver, USA arXiv \| \| competition \| challenge
	NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results Xin Li, Yeying Jin^†, Xin Jin, et al. (Organizer & Corresponding Author) Computer Vision and Pattern Recognition (CVPR), 2025, Nashville, USA arXiv \| \| bibtex \| slides \| video \| competition \| challenge
	Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal Yeying Jin, Xin Li, Jiadong Wang, Yan Zhang, Malu Zhang European Conference on Computer Vision (ECCV), 2024, Milan, Italy arXiv \| \| bibtex \| poster \| slides \| video \| competition \| challenge
	HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models Songtao Jiang, Yan Zhang, Yeying Jin, Zhihang Tang, Yangyang Wu, Yang Feng, Jian Wu, Zuozhu Liu^† Association for Computational Linguistics (ACL), 2025, Vienna, Austria arXiv \| bibtex
	Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering Songtao Jiang^, Chenyi Zhou^, Yan Zhang, Yeying Jin, Zuozhu Liu^† Association for Computational Linguistics (ACL), 2025, Vienna, Austria arXiv \| bibtex
	Modality-Fair Preference Optimization for Trustworthy MLLM Alignment Songtao Jiang, Yan Zhang, Ruizhe Chen, Tianxiang Hu, Yeying Jin, Qinglin He, Yang Feng, Jian Wu, Zuozhu Liu^† International Joint Conference on Artificial Intelligence (IJCAI), 2025, Montreal, Canada arXiv \| bibtex
	Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models Songtao Jiang^, Yan Zhang^, Chenyi Zhou, Yeying Jin, Yang Feng, Jian Wu, Zuozhu Liu^† ADHIP Best Paper Award, 2024, Jiaxing, China arXiv \| \| bibtex
	Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models Songtao Jiang^, Tuo Zheng^, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu^† EMNLP Findings, 2024, Miami, Florida arXiv \| \| bibtex
	Dual-Rain: Video Rain Removal using Assertive and Gentle Teachers Tingting Chen^, Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan European Conference on Computer Vision (ECCV)*, 2024, Milan, Italy paper \| bibtex
	UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt Xin Li^, Bingchen Li^, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren, Zhibo Chen^† European Conference on Computer Vision (ECCV), 2024, Milan, Italy arXiv \| \| bibtex
	NightHaze: Nighttime Image Dehazing via Self-Prior Learning Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2025, Philadelphia, USA arXiv \| \| bibtex \| Project Page
	SeD: Semantic-Aware Discriminator for Image Super-Resolution Bingchen Li^, Xin Li^, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen^† Computer Vision and Pattern Recognition (CVPR), 2024, Seattle, USA arXiv \| \| bibtex
	DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity Yeying Jin, Wei Ye, Wenhan Yang, Yuan Yuan, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada arXiv \| \| bibtex \| paper \| poster \| slides First diffusion-based shadow removal performs robustly on hard, soft and self shadows.
	NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Shunli Zhang, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2024, Vancouver, Canada arXiv \| bibtex \| poster
	Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression Yeying Jin, Wenhan Yang, Robby T. Tan European Conference on Computer Vision (ECCV), 2022, Tel Aviv, Israel arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video \| data \| link \| online demo Night image enhancement by enhancing low-light regions and suppressing light-effects regions.
	DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network Yeying Jin, Aashish Sharma, Robby T. Tan International Conference on Computer Vision (ICCV), 2021, Montreal, Canada arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video First unsupervised hard and soft shadow removal.
	Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution Yeying Jin^, Beibei Lin^, Wending Yan, Yuan Yuan, Wei Ye, Robby T. Tan ACM Multimedia (ACM'MM), 2023, Ottawa, Canada arXiv \| \| bibtex \| paper \| poster \| slides \| data First learning-based network handling nighttime haze and glow using APSF.
	Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning Yeying Jin, Ruoteng Li, Wenhan Yang, Robby T. Tan Association for the Advancement of Artificial Intelligence (AAAI), 2023, Washington DC, USA arXiv \| \| bibtex \| paper \| poster \| slides First reflectance layer estimation that performs robustly even in the presence of shadows and specularities.
	Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal Yeying Jin, Wending Yan, Wenhan Yang, Robby T. Tan Asian Conference on Computer Vision (ACCV), 2022, Macau, China arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| data Dense and/or non-uniform fog removal.

Jin Yeying