Weikai Huang

Hi, I am an undergrad at the University of Washington, advised by Prof. Ranjay Krishna, PhD student Jieyu Zhang, and PhD student Zixian Ma at UW CSE RAIVN Lab. Currently I am also a student collaborator at Allen Institute for AI working on VLM training and data generation.

Research Interests:

• 2D/3D Perception, Grounding, and Tracking in the Wild: Developing robust perception systems with diverse representations (points, 2D bboxes, 3D cuboids, 4D flows) that understand rigid, deformable, and articulated objects in unconstrained real-world environments. Building foundation spatial priors for downstream applications in fields like AR, autonomous systems, and embodied AI.

• Low-Level Perception and Spatial Understanding in VLMs/VLAs: Bridging world knowledge in LLMs with in-the-wild spatial priors and perception to build generalized systems that can reason about and act in the physical world, specifically in vision-language models (VLMs) and vision-language-action models (VLAs).

Beyond my core interests, I have worked on multi-modal agents and controllable generation and I’m always excited to explore and discuss ideas in other fields like NLP, ML, and RL.

📝 Publications

🎓 Education

• University of Washington
  B.S. in Computer Science, Minor in Applied Mathematics and Music
  2023 – 2027 (Expected)

📰 News

• [2024-9] Our work Task Me Anything is accepted to NeurIPS 2024.
• [2024-7] Our work m&m’s: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks is accepted to ECCV 2024.

🏅 Awards

• UW CSE John and JoAnne Wisniewski Endowed Scholarship 2024

📍 Professional Services

• Organizer of the Synthetic Data for Computer Vision Workshop at CVPR 2024 and CVPR 2025 (website)
• TA for UW CSE 455: Computer Vision, Autumn 2025 (course page)
• TA for UW CSE 493G: Deep Learning, Spring 2025 (course page)

📫 Contact

Email: weikaih@cs.washington.edu
Twitter (X): @weikaih04
Instagram: @weikaih04
Linkedin: Weikai Huang
Wechat: hwk18105962347