EN
Joya Chen

Joya Chen陈卓

字节跳动 Seed 研究科学家新加坡国立大学 博士

当前研究 visual coding agents

过往研究 流式 VLM · 测试时训练

研究

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

    Joya Chen, Zeyun Zhong, Mike Zheng Shou

    Paper Code zeyun-zhong/StreamTTT

  • 参与历代模型中流式能力的研发。

    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

    全部开源：模型、预训练与 SFT 数据、训练代码、评测基准和 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

    项目主页提供论文、代码、数据、Demo 与模型。

    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

* 共同第一作者 · 点击一行查看配图与链接

经历

教育

报告与服务

荣誉