Joya Chen （陈卓）

Hi! I’m Joya, a final-year Ph.D. candidate at the Show Lab, National University of Singapore (NUS), advised by Prof. Mike Shou. I will officially join ByteDance Seed this summer as a research scientist (Talent Program).

Previously, I interned with the VLM Base Model Team at ByteDance Seed. I also worked with Wei Li at TikTok AIIC, Huiyu Wang at Meta FAIR, and Zhaoyang Lv at Meta Reality Labs Research.

Currently, my research is on visual/video coding for agentic video understanding and generation. My prior research and expertise span streaming VLMs, VLM pre-training and post-training, video agents, audio generation, and test-time training.

View my education background

I obtained my bachelor's degree in School of Automotive Engineering, WUT. To chase my AI dream, I took the National Postgraduate Entrance Examination and obtained the 1st place in School of Computer Science and Technology, USTC. I obtained my master's degree from here, under the supervision of Prof. Enhong Chen, Prof. Tong Xu, and Prof. Dong Liu. I also had a research assistant at CVML@NUS group, working closely with Prof. Angela Yao.

Google Scholar  /  Github  /  Zhihu

profile photo
Activity
Image Student organizer of Bridging Vision, Language, and Action: What's Missing in Actionable Visual Perception for Robotics, CVPR 2026 Workshop. Videos will be available soon.
Image Invited talk at ByteDance Seed Video Gen (Seedance) Team on Learning Omni Video Stream. (Sorry, slides cannot be shared)
Image Core organizer of Multimodal Video Agent Workshop @ CVPR'25.

We have uploaded the recorded video of excellent talks given by
Prof. Song Han, Accelerating Large Language Models and Generative AI
Prof. Michael S. Ryoo, Multimodal Video Models for Robot Learning
Dr. Karl Pertsch, Training Multimodal Agents for Real Robot Manipulation at Scale
Prof. Yu Su, Augmenting Human Cognition with AI Agents that Use Computers
Prof. Katerina Fragkiadaki, Towards Grounded Reasoning in Multimodal Agents
Image Invited talk at Alibaba Qwen Team on VideoLLM-online: Online LLM for Streaming Video.
Image Core organizer of LOVEU: LOng-form VidEo Understanding Towards Multimodal AI Assistant and Copilot Workshop @ CVPR'24.

We have uploaded the recorded video:

Excellent talks given by Prof. Dima Damen, Prof. Marc Pollefeys, Dr. Chunyuan Li.

Great winner talks on Track1: Long-Term Video Question Answering and Track 2A: Text-Guided Video Editing & Track 2B: Text-to-Video Generation.
Research
Image Rethinking Expressivity and Efficiency in Test-Time Training
Zeyun Zhong, Joya Chen, Manuel Martin, Frederik Diederichs, Juergen Gall, Juergen Beyerer
arXiv, 2026
Paper / Code
Image StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
Joya Chen, Zeyun Zhong, Mike Zheng Shou
arXiv, 2026
Paper / Code
Image SeedRealtime: An Audio-Visual Full-Duplex LLM
ByteDance Seed. A native audio-visual full-duplex LLM.
Tech Blog, 2026
Homepage
Image Seed2.1 Model Card
ByteDance Seed. I contributed to the streaming capability.
Model Card, 2026
Homepage / Model Card
Image Seed2.0 Model Card
ByteDance Seed. I contributed to the streaming capability.
Model Card, 2026
Homepage / Model Card
Image Seed1.8 Model Card
ByteDance Seed. I contributed to the streaming capability.
Model Card, 2025
Homepage / Model Card
Image Seed1.5-VL Technical Report
ByteDance Seed. I contributed to the streaming capability and the interactive demo.
arXiv, 2025
Homepage / HuggingFace Demo / Github / API
Image LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
Joya Chen*, Ziyun Zeng*, Yiqi Lin*, Wei Li, Zejun Ma, Mike Zheng Shou
CVPR, 2025
All open-sourced! Checkpoints, Pre-training & SFT Datasets, Training Code, Evaluation Benchmark, Gradio Demo
Image VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Shiwei Wu*, Joya Chen*, Kevin Qinghong Lin, Qimeng Wang, Yan Gao, Qianli Xu, Tong Xu, Yao Hu, Enhong Chen, Mike Zheng Shou
NeurIPS, 2024
Image One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
Zechen Bai, Tong He, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, Lei Liu, Zheng Zhang, Mike Zheng Shou
NeurIPS, 2024
Code
Image Learning Video Context as Interleaved Multimodal Sequences
Kevin Qinghong Lin, Pengchuan Zhang, Difei Gao, Xide Xia, Joya Chen, Ziteng Gao, Jinheng Xie, Xuhong Xiao, Mike Zheng Shou
ECCV, 2024
Code
Image 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
CVPR, 2024
Homepage: Paper, Code, Data, Demo, Checkpoints
Image Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, ..., Mike Zheng Shou, Michael Wray
CVPR (Oral), 2024
https://ego-exo4d-data.org/
Image AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn
Difei Gao, Lei Ji, Luowei Zhou, Kevin Qinghong Lin, Joya Chen, Zihan Fan, Mike Zheng Shou
arXiv, 2023
Paper / Page
Image UniVTG: Towards Unified Video-Language Temporal Grounding
Kevin Qinghong Lin, Pengchuan Zhang, Joya Chen, Shraman Pramanick, Difei Gao, Alex Jinpeng Wang, Rui Yan, Mike Zheng Shou
ICCV, 2023
Paper / Code / Demo
Image Affordance Grounding from Demonstration Video to Target Image
Joya Chen, Difei Gao, Kevin Qinghong Lin, Mike Zheng Shou
CVPR, 2023
Paper / Code
Image DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
Joya Chen*, Kai Xu*, Yuhui Wang, Yifei Cheng, Angela Yao
ICLR, 2023
OpenReview / arXiv / Code
Image AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
Benita Wong*, Joya Chen*, You Wu*, Stan Weixian Lei, Dongxing Mao, Difei Gao, Mike Zheng Shou
ECCV, 2022
Paper / Page / Code / Challenge@CVPR'22
Image Is Heuristic Sampling Necessary in Training Deep Object Detectors?
Joya Chen, Dong Liu, Tong Xu, Shiwei Wu, Yifei Chen, Enhong Chen
IEEE Transactions on Image Processing, 2021
Paper / Code
Image Linking the Characters: Video-oriented Social Graph Generation via Hierarchical-cumulative GCN
Shiwei Wu, Joya Chen, Tong Xu, Liyi Chen, Lingfei Wu, Yao Hu, Enhong Chen
ACM MM (Oral), 2021
Paper
Engineering
Image Ranked 1st in HO-3D Leaderboard in Mesh Error/AUC and F@15mm metrics in Dec. 2020
Image Ranked 1st in PASCAL VOC Object Detection Competition 3 Leaderboard in Sep. 2018
Internship
Image

Thanks go to Jon Barron's website!