avatar

Kanghao Chen

Kanghao Chen in Chinese Ph.D. Student
The Hong Kong University of Science and Technology

Guangzhou, China

 kchen879@connect.hkust-gz.edu.cn


About Me

I am a final-year Ph.D. student at the AI Thrust (Information Hub) of HKUST (Guangzhou), jointly supervised by Prof. Ying-Cong Chen, Prof. Zeyu Wang and Prof. Lin Wang (@NTU). I am currently an intern at ByteDance Seed.

My work centers on multimodal generation, and extends to embodied intelligence and visual foundation models:

I am currently on the job market and open to research or engineering opportunities in multimodal AI. Please feel free to reach out by email.

Selected Publications

* equal contribution  Â·  † corresponding author
  1. ECCV
    DualCam: Dual-Branch Diffusion Model for Precise Camera-Controlled Video Generation
    Hongfei Zhang*, Kanghao Chen*, Zixin Zhang, Harold H. Chen, Shuai Yang, Yuqi Zhang, Ying-Cong Chen†
    European Conference on Computer Vision (ECCV), 2026.

  2. ECCV
    A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning
    Zixin Zhang*, Kanghao Chen*, Hanqing Wang*, Hongfei Zhang, Harold H. Chen, Chenfei Liao, Litao Guo, Ying-Cong Chen†
    European Conference on Computer Vision (ECCV), 2026.

  3. AAAI
    EvDiff3D: Event-Aware Diffusion Repair for High-Fidelity Event-Based 3D Reconstruction
    Kanghao Chen*, Zixin Zhang*, Lin Wang, Zeyu Wang†
    AAAI Conference on Artificial Intelligence (AAAI), 2026.

  4. TPAMI
    EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More
    Kanghao Chen*, Guoqiang Liang*, Yunfan Lu*, Hangyu Li, Lin Wang†
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
    Conference version: Towards Robust Event-guided Low-Light Image Enhancement, CVPR 2024 (Oral).

  5. RAL
    ExFMan: Rendering 3D Dynamic Humans with Hybrid Monocular Blurry Frames and Events
    Kanghao Chen, Zeyu Wang, Lin Wang†
    IEEE Robotics and Automation Letters (RAL), 2025.

  6. NeurIPS
    EVDiffuser: Event-Guided Consistent Video Reconstruction with Modality-Agnostic Diffusion Framework
    Kanghao Chen*, Zixin Zhang*, Guoqiang Liang, Lutao Jiang, Zeyu Wang, Ying-Cong Chen†
    The Conference on Neural Information Processing Systems (NeurIPS), 2025.

  7. NeurIPS
    LaSe-E2V: Towards Language-Guided Semantic-Aware Event-to-Video Reconstruction
    Kanghao Chen, Hangyu Li, Jiazhou Zhou, Zeyu Wang, Lin Wang†
    The Conference on Neural Information Processing Systems (NeurIPS), 2024.

  8. JBHI
    PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification
    Kanghao Chen*, Weixian Lei*, Rong Zhang, Ruixuan Wang†, and Wei-Shi Zheng
    IEEE Journal of Biomedical and Health Informatics (JBHI), 2023.

  9. ICME
    Improving Class Balancing at Both Feature Extractor and Classifier Head
    Kanghao Chen*, Huijuan Lu*, Ruixuan Wang†, and Wei-Shi Zheng
    IEEE International Conference on Multimedia and Expo (ICME), 2022.

  10. MICCAI
    Alleviating Data Imbalance Issue with Perturbed Input During Inference
    Kanghao Chen*, Yifan Mao*, Huijuan Lu, Chenghua Zeng, Ruixuan Wang†, and Wei-Shi Zheng
    International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021.

Research Experiences

Dec. 2025 - Present

ByteDance Seed, Intern

  • Working on multimodal generation and world models.
  • Building multimodal data pipelines and data scaling, and post-training models on the resulting data.
July. 2025 - Oct. 2025

Knowin, Intern

  • Developing VLM post-training for the Embodied Brain (KnowinBrain).
  • Building foundational infrastructure for data processing, model training, and evaluation.
July. 2022 - May. 2023

SenseTime AI Lab, Researcher

  • Working on human-centric foundation models, including 3D pose estimation and face reconstruction.

Education

Sep. 2023 - Present

HKUST (Guangzhou), Ph.D. in AI Thrust, Information Hub

Advised by Prof. Ying-Cong Chen, Prof. Zeyu Wang and Prof. Lin Wang (@NTU)
Sep. 2020 - June 2022

Sun Yat-sen University, M.Eng. in Computer Technology

Advised by Prof. Ruixuan Wang and Prof. Wei-Shi Zheng
Sep. 2016 - June 2020

Jinan University, B.Eng. in Computer Science and Technology

GPA 4.15/5.0 (top 2%)

Awards

Professional Services