Biography

Currently, I am a Research Lead at ByteDance Ads GenAI, where I work on Generative Foundation models.

I got my Master's degree from the Department of Computer Science and Engineering, Zhejiang University.

My previous research focus is on large scale open world visual understanding and pretraining in images & videos.

Research Interests

Visual Foundation Models, Generative Pretrain Models and Large Language Models.

Unified visual generation and understanding the complex world for computer vision.

Large-scale multi-modality generative Pretrain and Alignment.

Open world/vocabulary Visual Recognition : Equip vision with knowledge and semantics.

Highlights

  • Visual AutoRegressive modeling: a new visual generation Framework elevates Autoregrssive models beyond diffusion, indicate scaling law in image generation.

  • GLEE is accepted by CVPR 2024 as Highlight, An object-level foundation model for locating and identifying objects in images and videos.

  • UNINEXT unifies 10 instance perception tasks using a single model with the same model parameters

  • ByteTrack ranks 1th of the most influential papers in ECCV 2022. Code is available on github with 4.3k stars

  • Unicorn accepted by ECCV'22 as Oral Presentation . Unicorn accomplishes the great unification of the tracking network architecture and learning paradigm

  • Sparse R-CNN accepted by CVPR'21. Sparse R-CNN is integrated into several famous frameworks(Detectron2, MMDetection, PaddlePaddle)

I'm looking for self-motivated interns and full-time engineer/researcher for visual generative foundation models. Feel free to reach out if you are interested.

Publications [Google Scholar]

(* Equal contribution, Corresponding Author or Project Lead)

Conference and Preprint

Honors and Awards

  • Winner of CVPR 2022 Large-scale Video Object Segmentation Challenge: Video Instance Segmentation

  • Runner up of CVPR 2021 FGVC8 iNaturalist Challenge

  • Runner up of ICCV 2019 WIDER Face and Person Challenge: Face Detection

  • Excellent Mentor Award, ByteDance 2021

  • Outstanding Staff Award, Bytedance 2020, 2024

  • Competition Master in kaggle 2018

Professional Activities