Image Credit: Johns Hopkins University

Johns Hopkins University

Image Credit: Johns Hopkins University

Malone Hall

Image Credit: UCLA

University of California, Los Angeles

Previous Location of CCVL

The main goal of the CCVL (Computational Cognition, Vision, and Learning) research group is to develop mathematical models of vision and cognition. These models are intended primarily for designing artificial (computer) vision systems. Learning is required for extracting knowledge from data. Practical applications include vision for the disabled. These models also serve as computational models of biological vision which can be tested by behavioral methods and, in collaborative projects, with invasive, and non-invasive neuroscience techniques. We also study how humans and animals perform cognitive tasks such as learning and reasoning. In addition, we also use machine learning for interpreting medical images and studying brain function.

Latest News

All News →

Mar 11, 2026

Eight papers accepted by ICLR 2026

We have eight papers accepted to ICLR 2026! Congratulations to everyone involved! The full publication list will be updated here.

Mar 11, 2026

Eleven papers accepted by CVPR 2026

We have eleven papers accepted to CVPR 2026! Congratulations to everyone involved! The full publication...

Mar 10, 2026

Call for 2026 Summer Interns

We have multiple summer intern positions for world models, transformers architecture, medical image analysis, vision&language&action,...

Feb 01, 2026

Zongwei Zhou Awarded National Science Center Grant as External Investigator

Congratulations to Zongwei Zhou for being awarded a National Science Center Grant ($270K, 2026–2030) as...

Feb 2026

Dec 01, 2025

Zongwei Zhou Receives RSNA 2025 Certificate of Merit Award

Congratulations to Zongwei Zhou for receiving the Certificate of Merit Award at RSNA 2025! This...

Dec 2025

Scientists have become the bearers of the torch of discovery in our quest for knowledge.

Stephen Hawking Theoretical physicist - University of Cambridge

It has been said: The whole is more than the sum of its parts. It is more correct to say that the whole is something else than the sum of its parts, because summing up is a meaningless procedure, whereas the whole - part relationship is meaningful.

Kurt Koffka Psychologist

The critical act in formulating computational theories turns out to be the discovery of valid constraints on the way the world is structured -- constraints that provide sufficient information to allow the processing to succeed. The primitives of a representation are the most elementary units of shape information available in a representation.

David Marr Neuroscientist