Yubei Chen

Assistant Professor
Electrical and Computer Engineering Department, University of California, Davis
Room 3139, Kemper Hall, One Shields Avenue, Davis, CA 95616

I am an assistant professor in the ECE Department at University of California, Davis. Prior to joining UC Davis, I did my postdoc study with Prof. Yann LeCun at NYU Center for Data Science (CDS) and Meta Fundamental AI Research (FAIR). I completed my Ph.D. at Redwood Center for Theoretical Neuroscience and Berkeley AI Research (BAIR), UC Berkeley, advised by Prof. Bruno Olshausen. Undergraduate studies from Tsinghua University, Beijing. Co-founded Aizip Inc. that builds the world's smallest and most efficient AI models.

My research is at the intersection of computational neuroscience and deep unsupervised (self-supervised) learning, enhancing our understanding of the computational principles governing unsupervised representation learning in both brains and machines, and reshaping our insights into natural signal statistics.

I am actively looking for Graduate/Undergraduate students interested in unsupervised learning, generative models, and world models. Please email me your CV if you are interested in working with me.

news

Feb26, 2025	Neural Motion Simulator Pushing the Limit of World Models in Reinforcement Learning, is accepted at the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)! Paper coming soon!
Jan22, 2025	URLOST: Unsupervised Representation Learning without Stationarity or Topology, is accepted at the International Conference on Learning Representations (ICLR), 2025! Paper
Jan17, 2025	Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications, is accepted at the 2025 IEEE International Conference on Communications (ICC)! Paper
Oct9, 2024	Denoising for Manifold Extrapolation, is accepted at Workshop on Scientific Methods for Understanding Deep Learning (SciForDL) at NeurIPS 2024! Paper
Aug13, 2024	PICO-RAM: A PVT-Insensitive Analog Compute-In-Memory SRAM Macro With In Situ Multi-Bit Charge Computing and 6T Thin-Cell-Compatible Layout, is accepted at IEEE Journal of Solid-State Circuits (JSSC)! Paper
Jul3, 2024	Pose-aware self-supervised learning with viewpoint trajectory regularization, is accepted at European Conference on Computer Vision (ECCV) as an Oral presentation! Paper
Jun24, 2024	Insight: A Multi-modal Diagnostic Pipeline Using LLMs for Ocular Surface Disease Diagnosis, is accepted at International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)! Paper
Nov20, 2023	Unsupervised learning of structured representations via closed-loop transcription, is accepted at Conference on Parsimony and Learning (CPAL)! Paper
Nov14, 2023	Bag of Image Patch Embedding Behind the Success of Self-Supervised Learning, is accepted at Transactions on Machine Learning Research (TMLR)! Paper
Jun21, 2023	I have given an open lecture on unsupervised representation learning at TechBeat.net.