MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.

This technique could lead to safer autonomous vehicles, more efficient AR/VR headsets, or faster warehouse robots.

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.

The method uses language-based inputs instead of costly visual data to direct a robot through a multistep navigation task.

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.

The technique characterizes a material’s electronic properties 85 times faster than conventional methods.

A new approach could streamline virtual training processes or aid clinicians in reviewing diagnostic videos.

“Alchemist” system adjusts the material attributes of specific objects within images to potentially modify video game models to fit different environments, fine-tune VFX, and diversify robotic training.

Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.

Novel method makes tools like Stable Diffusion and DALL-E-3 faster by simplifying the image-generating process to a single step while maintaining or enhancing image quality.