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 received my Ph.D. 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 UESTC UESTC.

I have published papers at top international venues including SIGGRAPH Asia, CVPR, ICCV, ECCV, ICML, NeurIPS, ICLR and ACL, with . I have organized 6 workshops and 2 NTIRE challenges at CVPR, ECCV and AAAI, and given 30 invited talks, 9 of them at CVPR, ICCV, ICLR and AAAI. 📢 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	ActionRoPE: Action as Coordinates for Spatially Consistent Control in Planar-Camera Game World Models Zhiyang Deng, Yuzhe Wu, Zijun Lin, Yeying Jin^†‡ Project Page arXiv Model Encodes actions as world-coordinate rotary positions: 66% less revisit drift than the best baseline, across 1.3B–33B backbones.
arXiv 2026	GameDirector: Decoupling Gameplay Logic from Rendering for Player-Configurable Game World Models Zijun Lin, Zhiyang Deng, Yuzhe Wu, Bihan Wen, Yeying Jin^†‡ Project Page arXiv Model Dataset An agent runs game rules, states and NPC tactics; a video world model renders them, raising boss action quality by 39.9%+.
arXiv 2026	H3-World: Turning Language Understanding into World Control Danze Chen^, Zeqing Wang^, Ziyue Lin, Xingyi Yang^†, Yeying Jin^†‡ Project Page arXiv Link 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: Flexible Control and NPC Reactivity in 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: Simulating Cross-game Operations in Playable Environments for FPS World Models 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.
	Honor of Kings — AI Portrait, Detective & Esports Posters HOK Flowborn Dimensional Editor • 2025.06–Present 22.5K players · 2.1M posters generated Shipped in-game — Battle Loading, In-Game Hero, In-Game Popup · 80% in-game display 99% positive sentiment · one-click sharing to HOK Camp, X, Instagram, Facebook 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

Filters

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^† 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 MM, 2026, Rio de Janeiro, Brazil arXiv \| Project Page Mask-free video try-on learned from image-level pseudo data; released with the OmniView dataset.
arXiv 2026	StoryEngine: A State-Grounded Agentic Framework for Video Storytelling Yingrui Wang^, Zeqing Wang^, Yeying Jin^†‡ arXiv preprint, 2026 arXiv \| \| Project Page Tracks story state across shots so each event carries forward, keeping long multi-shot videos causally coherent and consistent.
arXiv 2026	Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Meng Chu^, Xuan Billy Zhang^, Kevin Qinghong Lin^, …, Yeying Jin, …, Ziwei Liu^†, Philip Torr^†, Jiaya Jia^† Show All Authors Show Fewer 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
arXiv 2026	AI for Games in the Foundation Model Era Meng Luo, Yanlin Li, Hao Li, Hongzhan Lin, Pengfei Zhou, Tianjie Ju, Ran Zhang, Yeying Jin, Mong-Li Lee, Wynne Hsu arXiv preprint, 2026 arXiv \| \| Project Page Organizes AI across the whole game lifecycle into six roles — playing, modeling, designing, building, runtime adaptation and evaluation — and maps how outputs transfer between them.
ECCV 2026	MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation Yinhan Zhang^, Dingwei Tan^, Xianghao Kong, Yue Ma^‡, Yeying Jin^†, Anyi Rao^† 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^† 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 MM, 2026, Rio de Janeiro, Brazil arXiv \| \| Project Page
arXiv 2026	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 \|
ICML 2026	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 ICML, 2026, Seoul, South Korea arXiv \|
CVPR Findings 2026	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 CVPR Findings, 2026, Denver, USA arXiv \|
CVPR Findings 2026	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^‡ 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 ECCV, 2026, Malmö, Sweden arXiv \| \| Project Page
AAAI 2026	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^† 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
ICLR 2026	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^† ICLR*, 2026, Rio de Janeiro, Brazil arXiv \| \| bibtex \| Project Page \| online demo \| video \| link
PR 2025	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
CVPR 2026	Unpaired Image Deraining Using Reward-Guided Self-Reinforcement Strategy Yinghao Chen, Yeying Jin^†‡, Xiang Chen, Yanyan Wei^†, Ziyang Yan, Yaowen Fu CVPR, 2026, Denver, USA arXiv
ICCV 2025	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^† ICCV, 2025, Honolulu, USA paper \| bibtex
ACM MM 2025	DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy Qirui Yang^, Fangpu Zhang^, Yeying Jin, Qihua Cheng, Pengtao Jiang, Huanjing Yue^†, Jingyu Yang^† ACM MM, 2025, Dublin, Ireland arXiv \| \| bibtex
CVPR 2025	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^† CVPR, 2025, Nashville, USA arXiv \| \| bibtex \| Project Page \| online demo \| link
CVPRW 2026	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) CVPR Workshops (CVPRW), 2026, Denver, USA arXiv
CVPRW 2026	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) CVPR Workshops (CVPRW), 2026, Denver, USA arXiv \| \| competition \| challenge
CVPRW 2025	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) CVPR Workshops (CVPRW), 2025, Nashville, USA arXiv \| \| bibtex \| slides \| video \| competition \| challenge
ECCV 2024	Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal Yeying Jin, Xin Li, Jiadong Wang, Yan Zhang, Malu Zhang ECCV, 2024, Milan, Italy arXiv \| \| bibtex \| poster \| slides \| video \| competition \| challenge
ACL 2025	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^† ACL, 2025, Vienna, Austria arXiv \| bibtex
ACL 2025	Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering Songtao Jiang^, Chenyi Zhou^, Yan Zhang, Yeying Jin, Zuozhu Liu^† ACL, 2025, Vienna, Austria arXiv \| bibtex
IJCAI 2025	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^† IJCAI, 2025, Montreal, Canada arXiv \| bibtex
ADHIP 2024	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, 2024, Jiaxing, China, Best Paper Award arXiv \| \| bibtex
EMNLP Findings 2024	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, USA arXiv \| \| bibtex
ECCV 2024	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 ECCV*, 2024, Milan, Italy paper \| bibtex
ECCV 2024	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^† ECCV, 2024, Milan, Italy arXiv \| \| bibtex
AAAI 2025	NightHaze: Nighttime Image Dehazing via Self-Prior Learning Beibei Lin^, Yeying Jin^, Wending Yan, Wei Ye, Yuan Yuan, Robby T. Tan AAAI, 2025, Philadelphia, USA arXiv \| \| bibtex \| Project Page
CVPR 2024	SeD: Semantic-Aware Discriminator for Image Super-Resolution Bingchen Li^, Xin Li^, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen^† CVPR, 2024, Seattle, USA arXiv \| \| bibtex
AAAI 2024	DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity Yeying Jin, Wei Ye, Wenhan Yang, Yuan Yuan, Robby T. Tan AAAI, 2024, Vancouver, Canada arXiv \| \| bibtex \| paper \| poster \| slides The first diffusion-based shadow removal method, robust to hard, soft and self shadows.
AAAI 2024	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 AAAI, 2024, Vancouver, Canada arXiv \| bibtex \| poster
ECCV 2022	Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression Yeying Jin, Wenhan Yang, Robby T. Tan ECCV, 2022, Tel Aviv, Israel arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video \| data \| link \| online demo Unsupervised night image enhancement that boosts low-light regions while suppressing glare and glow.
ICCV 2021	DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network Yeying Jin, Aashish Sharma, Robby T. Tan ICCV, 2021, Montreal, Canada arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| video The first unsupervised method to remove both hard and soft shadows from a single image.
ACM MM 2023	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 MM, 2023, Ottawa, Canada arXiv \| \| bibtex \| paper \| poster \| slides \| data The first learning-based method to remove nighttime haze and glow jointly, guided by the APSF.
AAAI 2023	Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning Yeying Jin, Ruoteng Li, Wenhan Yang, Robby T. Tan AAAI, 2023, Washington, DC, USA arXiv \| \| bibtex \| paper \| poster \| slides The first single-image reflectance estimation that stays robust under shadows and specular highlights.
ACCV 2022	Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal Yeying Jin, Wending Yan, Wenhan Yang, Robby T. Tan ACCV, 2022, Macao, China arXiv \| \| bibtex \| paper \| supp \| poster \| slides \| data Removes dense, non-uniform fog using structure representation and uncertainty feedback learning.

Organizer

6 workshops and 2 NTIRE challenges at CVPR, ECCV and AAAI.

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 Denver, USA
CVPR 2026 AGENTIC Workshop	Workshop on Agentic AI for Visual Media	06.03.2026 Denver, USA
CVPR 2026 URVIS Workshop	Unified Robotic Vision with Cross-Modal Sensing and Alignment	06.04.2026 Denver, USA
CVPR 2026 AIGENS Workshop	The 3rd Workshop on AI for Content Generation, Quality Enhancement and Streaming	06.03.2026 Denver, USA
CVPR 2026 NTIRE Challenge	The 2nd Challenge on Day and Night Raindrop Removal for Dual-Focused Images	06.04.2026 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

9 talks at CVPR, ICCV, ICLR and AAAI, among 30 invited talks in total.

Host	Topic	Date & Venue
2026
NUS CEG5304 Deep Learning Guest Lecture invited by Yuecong Xu	World Model and Agentic Video Generation	Nov Singapore
NTU PhD Course: Deep Learning for Data Science, Guest Lecture invited by Ziwei Liu	Game World Model	Oct 15 Singapore
NUS ECE SAMI Seminar invited by Yuecong Xu	Game World Model and Coding Agents	Oct 14 Singapore
Runway invited by Robin Kahlow	Game World Model	Jun 26 Singapore
CVPR 机器之心	Invited Talk (w/ Ziwei Liu^NTU, Mike Zheng Shou^NUS, Ruoshi Liu^UMD)	Jun 6 Denver, USA
CVPR 2026 URVIS invited by Zongwei Wu	World Model	Jun 4 Denver, USA
CVPR 2026 AGENTIC invited by Jinjin Gu	Game World Model	Jun 3 Denver, USA
CVPR 2026 AIGENS invited by Marcos V. Conde	Game World Model for Video Generation	Jun 3 Denver, USA
CVPR 2026 NTIRE invited by Zongwei Wu	Game World Model	Jun 3 Denver, USA
SPARK Share	From Video Generation to World Model	May 22 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)	May 16 Singapore
ICLR Booth Talk Game Session Talk	From AIGC to World Model	Apr 25 Rio de Janeiro, Brazil
NUS EE6934 Emerging Topics in AI and Deep Learning Guest Lecture invited by Xinchao Wang	From AIGC to World Model	Mar 17 Singapore
AAAI invited by Xin Li	From Creation to Perception: Generative AI for Content Generation	Jan Singapore
Low-level Community invited by Xiang Chen	AIGC-Powered Game Marketing: From Generation to Deployment	Jan Singapore
2025
Programmers Video	Exploring Sora: Unlocking the Core of AI Video Creation [Video]	Nov Singapore
ICCV AIGENS invited by Marcos V. Conde	From Creation to Perception: Generative AI for Content Generation	Oct Honolulu, USA
Tencent	AI Video Gen \| When Wukong meets Yayoi Kusama	May Singapore
ICLR invited by Kevin Qinghong Lin	AI × Gaming: Creative Applications of AIGC [Video]	Apr Singapore
Tencent	AI Generation: Inspiring Game Marketing and Development	Feb Singapore
2024
AI TIME	Raindrop Clarity: Dual-Focused, Day and Night	Sep
AI TIME	Shadow Removal using Diffusion Model	Jan
2023
Tencent	Applications of Generative AI	Nov Singapore
Huawei	Visibility Enhancement using Generative Model	Jul
Adobe invited by Eric Kee	NextCam Reading Group: Light-effects Suppression	Jul USA
Huawei	Image/Video Restoration and Generation	Mar
AI TIME	Intrinsic Image Decomposition	Feb
ByteDance invited by Hanshu Yan	Diffusion Model in Image Processing	Jan
2022
Huawei	Visibility Enhancement in Nighttime	Dec Singapore
AI TIME	Unsupervised Image Restoration and Generation	Nov

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
CVPR 2025 NTIRE赛事 \| 首届多场景雨滴去除挑战赛	06.2025
AI赋能UGC \| 点亮每一位玩家的英雄梦	05.2025
Sora揭秘: OpenAI文生视频模型, Diffusion+Transformer带来的思考	02.2024
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.Sc. (Electrical and Computer Engineering), NUS, Singapore
09.2013-07.2017: B.Eng. (Electronic Information Engineering), UESTC, China (GPA: 3.93/4.00)

Work and Internship 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, NeurIPS 2019 Expo demo.

Honors and Awards

“Yayoi Kusama × Wukong”, ModelScope Wan 2.1 Video Generation Challenge — 2nd Place
Tencent Knowledge, Excellent R&D, Outstanding Mentor and Outstanding Contributor Awards
ICML 2026 Gold Reviewer Award
Best Paper Award, ADHIP 2024
AI Singapore (AISG) Ph.D. Fellowship — Theme: Continuous Learning AI, Self-supervised Learning

Professional Services

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

Jin Yeying