Researchers leverage shadows to model 3D scenes, including objects blocked from view
This technique could lead to safer autonomous vehicles, more efficient AR/VR headsets, or faster warehouse robots.
Research
Understanding the visual knowledge of language models
LLMs trained primarily on text can generate complex visual concepts through code with self-correction. Researchers used these illustrations to train an image-free computer vision system to recognize real photos.
A smarter way to streamline drug discovery
The SPARROW algorithm automatically identifies the best molecules to test as potential new medicines, given the vast number of factors affecting each choice.
Technique improves the reasoning capabilities of large language models
Combining natural language and programming, the method enables LLMs to solve numerical, analytical, and language-based tasks transparently.
Researchers use large language models to help robots navigate
The method uses language-based inputs instead of costly visual data to direct a robot through a multistep navigation task.
Making climate models relevant for local decision-makers
A new downscaling method leverages machine learning to speed up climate model simulations at finer resolutions, making them usable on local levels.
New algorithm discovers language just by watching videos
DenseAV, developed at MIT, learns to parse and understand the meaning of language just by watching videos of people talking, with potential applications in multimedia search, language learning, and robotics.
New computer vision method helps speed up screening of electronic materials
The technique characterizes a material’s electronic properties 85 times faster than conventional methods.
Mouth-based touchpad enables people living with paralysis to interact with computers
The startup Augmental allows users to operate phones and other devices using their tongue, mouth, and head gestures.
A technique for more effective multipurpose robots
With generative AI models, researchers combined robotics data from different sources to help robots learn better.