Yun-Chun Chen

Yun-Chun Chen

Generative AI Researcher

Adobe Firefly Foundry

I am a Generative AI Researcher at Adobe Firefly Foundry, where I build world models and custom generative AI models.

Previously, I was an Applied Scientist at Amazon AWS, where I built AI agents and vision foundation models.

My research interests include World Models, Generative AI, Multimodal LLMs, and Agentic AI.

I received a Ph.D. in Computer Science from the University of Toronto, where I was advised by Alec Jacobson, and a B.S. in Electrical Engineering from National Taiwan University.

Email: yunchunchen.work@gmail.com

Google Scholar GitHub LinkedIn Twitter / X CV

Publications

Text-guided Controllable Mesh Refinement teaser
ACM SIGGRAPH Asia 2024

Text-guided Controllable Mesh Refinement for Interactive 3D Modeling

Yun-Chun Chen, Selena Ling, Zhiqin Chen, Vladimir G. Kim, Matheus Gadelha, Alec Jacobson

Paper Project Page Poster Slides
Grasp'D teaser
ECCV 2022

Grasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered Hands

Dylan Turpin, Liquan Wang, Eric Heiden, Yun-Chun Chen, Miles Macklin, Stavros Tsogkas, Sven Dickinson, Animesh Garg

Oral Presentation

Paper Project Page Code Video Poster Twitter
Neural Motion Fields teaser
RSS Workshop 2022

Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions

Yun-Chun Chen*, Adithyavairavan Murali*, Balakumar Sundaralingam*, Wei Yang, Animesh Garg, Dieter Fox

Spotlight Talk

Paper Video Slides Twitter
Learning by Watching teaser
IROS 2021

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos

Haoyu Xiong, Quanzhou Li, Yun-Chun Chen, Homanga Bharadhwaj, Samarth Sinha, Animesh Garg

Paper Project Page Video Twitter
Show Match and Segment teaser
IEEE TPAMI 2021

Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation

Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang

Paper Project Page Code Slides
Self-Attentive 3D Human teaser
CVIU 2021

Self-Attentive 3D Human Pose and Shape Estimation from Videos

Yun-Chun Chen, Marco Piccirilli, Robinson Piramuthu, Ming-Hsuan Yang

Paper
Learning to Learn 3D Shape Completion teaser
ECCV 2020

Learning to Learn in a Semi-Supervised Fashion

Yun-Chun Chen, Chao-Te Chou, Yu-Chiang Frank Wang

Paper
Cross-Resolution Adversarial Dual Network teaser
arXiv preprint

Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

Yun-Chun Chen*, Yu-Jhe Li*, Yen-Yu Lin, Yu-Chiang Frank Wang

Paper
Recover and Identify teasers
ICCV 2019

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-ID

Yun-Chun Chen*, Yu-Jhe Li*, Yen-Yu Lin, Xiaofei Du, Yu-Chiang Frank Wang

Paper Slides Poster
CrDoCo teaser
CVPR 2019

CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang

Paper Project Page Code Slides Poster
Learning Resolution-Invariant Features teaser
AAAI 2019

Learning Resolution-Invariant Deep Representations for Person Re-Identification

Yun-Chun Chen*, Yu-Jhe Li*, Xiaofei Du, Yu-Chiang Frank Wang

Oral Presentation

Paper Slides Poster
Deep Semantic Matching teaser
ACCV 2018

Deep Semantic Matching with Foreground Detection and Cycle-Consistency

Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu, Jia-Bin Huang, Ming-Hsuan Yang, Yen-Yu Lin

Paper Project Page Code Poster