中文
Joya Chen

Joya Chen陈卓

Research Scientist @ ByteDance SeedPh.D. @ National University of Singapore

Current research visual coding agents

Past research streaming VLMs · test-time training

Research

  • StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs

    Joya Chen, Zeyun Zhong, Mike Zheng Shou

    Paper Code zeyun-zhong/StreamTTT

  • Contributed to the streaming capability across releases.

    SeedRealtime Seed2.1 Seed2.0 Seed1.8 Seed1.5-VL
  • LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

    Joya Chen*, Ziyun Zeng*, Yiqi Lin*, Wei Li, Zejun Ma, Mike Zheng Shou

    Fully open-sourced: checkpoints, pre-training & SFT data, training code, benchmark and demo.

    Project showlab/livecc
  • VideoLLM-online: Online Video Large Language Model for Streaming Video

    Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, Mike Zheng Shou

    Paper, code, data, demo and checkpoints on the project page.

    Project showlab/videollm-online
  • Affordance Grounding from Demonstration Video to Target Image

    Joya Chen, Difei Gao, Kevin Qinghong Lin, Mike Zheng Shou

    Paper Code showlab/afformer
  • DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

    Joya Chen*, Kai Xu*, Yuhui Wang, Yifei Cheng, Angela Yao

    OpenReview arXiv Code chenjoya/dropit

* Equal contribution · Click a row for its figure and links

Experience

  • 2025 – ByteDance Seed · Research Intern → Research Scientist
  • 2024 – 25 TikTok AIIC · Research Intern with Wei Li
  • 2023 – 24 Meta FAIR · Research Intern with Huiyu Wang
  • 2023 Meta Reality Labs Research · Research Intern with Zhaoyang Lv

Education

Talks & service

Honors