Shan Yang

Shan Yang

Staff Applied Scientist, Adobe Firefly | Ex-Tech Lead Amazon AI Studio | Xoogler

I am a Staff Applied Scientist at Adobe working on Firefly, Adobe's family of generative AI models. Previously I was a Tech Lead at Amazon where I drove AI Studio and led Amazon Video Search, LLM reranking for Product Search, and multi-modal LLM research. My broader interests span multi-modality perception, 3D computer vision, and physically based simulation.

Before Amazon, I was a Senior Research SDE at Google Research focusing on multi-modal content creation and 3D vision. I completed my PhD at UNC-CH under Prof. Ming C. Lin.

alexyangshan@gmail.com Resume

Publications

TTC-Net

Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control

Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang Wang, Ming Lin, René Vidal

arXiv 2025

arXiv project
VLAP

Schema Perception for Robust Video Question Answering

Xijun Wang, Shan Yang

Internal 2025

paper
VLAP

VLAP: Efficient Video-Language Alignment via Frame Prompting and Distilling for Video Question Answering

Xijun Wang, Junbang Liang, Chun-Kai Wang, Kenan Deng, Yu Lou, Ming Lin, Shan Yang

ECCV 2024

arXiv
ICAR

ICAR: Image-based Complementary Auto Reasoning

Xijun Wang, Anqi Liang, Junbang Liang, Ming Lin, Yu Lou, Shan Yang

AAAI 2024

arXiv
MeSa

MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation

Muhammad Osama Khan, Junbang Liang, Chun-Kai Wang, Shan Yang, Yu Lou

NIPS 2023 Workshop SSLTheoryPractice

arXiv
RoSI

RoSI: Recovering 3D Shape Interiors from Few Articulation Images

Akshay Gadi Patil, Yiming Qian, Shan Yang, Brian Jackson, Eric Bennett, Hao Zhang

In submission

arXiv
MBT

Attention Bottlenecks for Multimodal Fusion

Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, Chen Sun

NeurIPS 2021

arXiv
Optical Mouse

Optical Mouse: 3D Mouse Pose From Single-View Video

Shan Yang*, Bo Hu*, David A. Ross, Avneesh Sud, Yi Liu, Graham Ruby, Bryan Seybold

CVPR 2021 (CV4Animal Workshop)

AI Choreographer

AI Choreographer: Music Conditioned 3D Dance Generation with AIST++

Shan Yang*, Ruilong Li*, David A. Ross, Angjoo Kanazawa

ICCV 2021

arXiv Project
Cloth Material Recovery

Learning-based Cloth Material Recovery from Video

Shan Yang, Junbang Liang, Ming C. Lin

ICCV 2017

Paper Video
Garment Recovery

Physics-Inspired Garment Recovery from a Single-View Image

Shan Yang, Zherong Pan, Tanya Amert, Ke Wang, Licheng Yu, Tamara Berg, Ming C. Lin

ACM TOG 2018

Paper Video
Referring Expressions

Modeling Context in Referring Expressions

Licheng Yu, Patric Poirson, Shan Yang, Alex Berg, Tamara Berg

ECCV 2016

Paper Dataset Project
Prostate Cancer Classification

Classification of Prostate Cancer Grades and T-Stages based on Tissue Elasticity Using Medical Image Analysis

Shan Yang, Vladimir Jojic, Jun Lian, Ronald Chen, Hongtu Zhu, Ming C. Lin

MICCAI 2016

Paper Project Supplementary
Bayesian Estimation

Bayesian Estimation of Non-Rigid Mechanical Parameters Using Temporal Sequences of Deformation Samples

Shan Yang, Ming C. Lin

ICRA 2016

Video Paper
MaterialCloning

MaterialCloning: Acquiring Elasticity Parameters from Images for Medical Applications

Shan Yang, Ming C. Lin

IEEE TVCG 2016

Project Paper
Simultaneous Estimation

Simultaneous Estimation of Elasticity for Multiple Deformable Bodies

Shan Yang, Ming C. Lin

Computer Animation and Virtual Worlds, 2015

Project Paper
Buried Suture

Real-time simulation for buried suture

Shan Yang, Wenlong Lu, Lixu Gu

CARS 2012

Projects

Lumi Research Manager

AI-powered research project manager with pixel-art agent teams (Scout, Theorist, Architect, Coder, and more)

Multimodal Content Creation Training Infrastructure (MINT)

Supporting multimodal dance generation

AIST++ Dataset API

Developer tools and loaders for the AIST++ dataset

Diffusion from Scratch

Educational implementation of diffusion models

CocoCut App

Interactive creation and editing app