About
I am currently a postdoctoral fellow at Contextual Robotics Institute in UC San Diego lead by
Prof. Xiaolong Wang.
Previously, I obtained Ph.D. degree at Computer Science Department in University of Wisconsin,
Madison in 2024 Spring,
fortunate to be supervised by
Prof. Yong Jae Lee.
During my PhD, I was grateful to closely working with Dr. Jianwei Yang in Microsoft Research.
Prior to this, I started the doctoral jounrney at UC Davis, advised by
the same supervisor
and worked closely with Dr. Fanyi
Xiao. Previously, I received my B.S. degree from Hong Kong Baptist University in 2018, during which I was fortunate to intern at CMU with Dr. Zhiding Yu.
My current research focuses are:
(1) EmbodiedAI/Robotics: Navigation, Manipulation, and Perception.
(2) Building Generalist Multimodal Foundation Models.
(3) General Representation Learning (2D/3D).
Feel free to email me at xueyanzoucs AT gmail.com if you're interested in collaboration (open to undergraduates, graduates, institutions/companies globally).
Last Updated: Nov, 2024
News
🍒 [2024.09] FIND is accepted by NeurIPS24, GraspSplat is accepted by CoRL24, Semantic-SAM, LLaVA-Grounding, LLaVA-Plus are accepted by ECCV24, DINOv is accetped by CVPR24.
🐡 [2024.07] We are organizing the Efficient Deep Learning for Foundation Models workshop in ECCV24.
🍆 [2024.06] We are organizing the 3nd Computer Vision in the Wild workshop in CVPR24, Seattle.
🥝 [2024.05] I received NSF TILOS postdoctoral fellowship from UC San Diego.
🍓 [2023.10] We have released full stack Training, Evaluation, and Demo code for SEEM.
🍉 [2023.09] Our proposal has been accepted to Microsoft's Accelerate Foundation Models Research Program, with topic Advancing Foundation Models: Bridging Human Cognition and
IoT Sensing.
🍊 [2022.12] We released X-Decoder, a generalist model for decoding pixel-level
masks and token-level semantics seamlessly. Please try out our All-In-One and Instruct X-Decoder demo!
🥕 [2020.07] Our paper "Delving Deeper into Anti-Aliasing in ConvNets" has been accepted to BMVC2020 with Best Paper Award.
▶
Show more news
🍇 [2023.06] We are organizing demo session with topic "Interactive X-Decoder for Understanding and
Generating Pixel, Image, and Language" in CVPR 2023.
🍎 [2023.03] We are organizing SGinW challenge in the 2nd Computer Vision in
the Wild (CVinW) Workshop at CVPR 2023! Welcome to submit your
numbers.
Experience
