Skip to content
View kairunwen's full-sized avatar
💫
Good Luck！
💫
Good Luck！
105 followers · 481 following

Achievements

Achievement: Starstruckx2

Achievements

Achievement: Starstruckx2

Block or report kairunwen

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kairunwen/README.md

Hi, I'm Kairun Wen (温凯润) 👋

Kairun Wen

I'm a first-year Ph.D. student at MMLab, The Chinese University of Hong Kong, advised by Prof. Hongsheng Li.

My long-term goal is to develop embodied foundation models with multimodal spatial intelligence. I aim to enable robot-use agents to understand and model the dynamic physical world, plan and act through robotic skills and tools, and adapt through interaction and feedback.

Email · X · RedNote · LinkedIn · Google Scholar


Selected Research

  • Thinking in Dynamics — Evaluating how MLLMs perceive, track, and reason about dynamics in the physical 4D world.
  • DynamicVerse — Physically-aware multimodal 4D world modeling.
  • InstantSplat — Sparse-view, SfM-free 3D Gaussian reconstruction.

Resources

  • Awesome Robot-Use Agent — Papers, research articles, tools, benchmarks, and community demos for robot-use agents.

I'm happy to connect with researchers working on Robot-use Agent · Embodied Foundation Model · Spatial intelligence.

Pinned Loading

  1. NVlabs/InstantSplat NVlabs/InstantSplat Public

    InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

    Python 1.7k 156

  2. VITA-Group/LightGaussian VITA-Group/LightGaussian Public

    [NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

    Python 821 76

  3. Dynamics-X/DynamicVerse Dynamics-X/DynamicVerse Public

    [NeurIPS 2025]"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling"

    Python 103 4

  4. Awesome-Robot-Use-Agent Awesome-Robot-Use-Agent Public

    A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.

    Python 129