Yan Kang

Senior Research Engineer II, Research Manager

Seattle

Yan is a Senior Research Engineer & Manager in the Research Engineering and Design Lab at Adobe Research. He spearheads efforts to streamline computational costs across Adobe’s models at various scales by leveraging efficient attentions, sparse MoE, autoregressive video model, Neural Architecture Search, pruning, distillation, caching, KV compression, post-training inference optimization, etc. To push efficiency to its limits, Yan also works on optimizing the heavy cloud-serving models for on-device deployment, enabling high-performance solutions on edge devices. He is a technical lead and works with a group of researchers and machine learning engineers to conduct model efficiency efforts. The team’s techniques form core layers of Adobe’s foundation model, enabling scaling to unprecedented capacities, resolutions, and video durations.

Contact: yankang [at] adobe [dot] com

News

  • Sep. 2025. We are hiring multiple full-time and interns for Research Scientist/Engineer positions.
  • Mar. 2025. Our video model blog is released, proud to share that I’m one of the seven Research Foundation core members.
  • Nov. 2024. I’m hiring multiple interns for different topics related to GenAI efficiency.
  • Sep. 2024. Won Adobe Tech Excellence Award, among the few recipients worldwide.

Tech Transfers

  • Firefly 1.0
  • Firefly 2.0
  • GenerativeFill 1.0
  • GenerativeFill 3.0
  • MetaCAF (Content Aware Fill)
  • SuperCAF (Content Aware Fill)
  • Wire segmentation
  • Panoptic segmentation
  • Select person
  • On-device image inpainting
  • On-device image super-resolution
  • On-device video super-resolution
  • In-browser panoptic segmentation

Previous graduated interns

Publications

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

Dedhia, Bhishma., Bourgin, David., Singh, Krishna., Li, Yuheng., Kang, Yan., Xu, Zhan., Jha, Niraj., Liu, Yuchen. (Oct. 19, 2025)

ICCV 2025

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Ding, Zihan., Jin, Chi., Liu, Difan., Zheng, Haitian., Singh, Krishna., Zhang, Qiang., Kang, Yan., Lin, Zhe., Liu, Yuchen. (Oct. 19, 2025)

ICCV 2025

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

You, Haoran., Barnes, Connelly., Zhou, Yuqian., Kang, Yan., Du, Zhenbang., Zhou, Wei., Zhang, Lingzhi., Nitzan, Yotam., Liu, Xiaoyang., Lin, Zhe., Shechtman, Eli., Amirghodsi, Sohrab., Lin, Yingyan. (Jun. 10, 2025)

Conference on Computer Vision and Pattern Recognition (CVPR 2025)

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

Ganjdanesh, Alireza., Kang, Yan., Liu, Yuchen., Zhang, Richard., Lin, Zhe., Huang, Heng. (Oct. 1, 2024)

European Conference on Computer Vision (ECCV 2024)

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

Li, Zhengang., Kang, Yan., Liu, Yuchen., Liu, Difan., Hinz, Tobias., Liu, Feng., Wang, Yanzhi. (Jun. 19, 2024)

CVPR 2024

AT-EDM: Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Wang, Hongjie., Liu, Difan., Kang, Yan., Li, Yijun., Lin, Zhe., Jha, Niraj., Liu, Yuchen. (Jun. 17, 2024)

CVPR 2024