Image
Using language to give robots a better grasp of an open-ended world
CSAIL article

Imagine you’re visiting a friend abroad, and you look inside their fridge to see what would make for a great breakfast. Many of the items initially appear foreign to you, with each one encased in unfamiliar packaging and containers. Despite these visual distinctions, you begin to understand what each one is used for and pick them up as needed.

Category
Graphic & Vision
Language
Python
Project Lead
Tommi S. Jaakkola

PFGM++ unlocks the potential of physics-inspired generative models.

NVIDIA
Last Updated
Category
Graphic & Vision
Language
Python
Project Lead
Polina Golland

NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction (both rigid and deformable).

MIT License
Last Updated
Category
Graphic & Vision
Language
Python
Project Lead
Polina Golland

A public AI tool to turn heterogeneous clinical brain scans into high-resolution T1-weighted images for 3D morphometry.

Apache-2.0 license
Last Updated
Category
Graphic & Vision
Language
Python
Project Lead
Jim Glass

ContentVec is an improved self-supervised speech representation by disentangling speakers.

MIT License
Last Updated
Category
Graphic & Vision
Language
Python
Project Lead
Jim Glass

UAVM achieves a new state-of-the-art audio-visual event classification accuracy of 65.8% on VGGSound. 

BSD 2-Clause "Simplified" License
Last Updated
Category
Graphic & Vision
Language
C
Project Lead
Erik Demaine

Lets glass blowers design and visualize glass cane, and to get a sense of what that cane will look like on a blown piece.

MIT License
Last Updated
Category
Graphic & Vision
Language
CoffeeScript
Project Lead
Erik Demaine

Cocreate is a web-based shared whiteboard tool for drawing, teaching, and brainstorming together with others.

MIT License
Last Updated