Skip to main content
  • For Students
  • For Industry
  • For Members
  • Accessibility
  • Login
MIT CSAIL
  • Research
  • People
  • News
  • Events
  • Symposia
  • Forum
  • About
  • Research
  • People
  • News
  • Events
  • Symposia
  • Forum
  • About
  • For Students
  • For Industry
  • For Members
  • Accessibility
  • Login
  • Contact
  • Press Requests
  • Accessibility

News

SketchAgent uses a multimodal language model to turn natural language prompts into sketches in a few seconds. It can doodle on its own or through collaboration, drawing with a human or incorporating text-based input to sketch each part separately (Credits: Alex Shipps/MIT CSAIL, with AI-generated sketches from the researchers).

Teaching AI models the broad strokes to sketch more like humans do

The CausVid model can quickly generate clips from a simple text prompt, creating many imaginative and artistic scenes (Credits: Alex Shipps/MIT CSAIL, using AI-generated images from the researchers).

Hybrid AI model crafts smooth, high-quality videos in seconds

“Linear oscillatory state-space models” leverage principles of forced harmonic oscillators — a concept deeply rooted in physics and observed in biological neural networks. This can improve how we predict complex information like climate trends or financial data (Credit: Pixabay).

Novel AI model inspired by neural dynamics from the brain

Spotlighted News

Teaching AI models the broad strokes to sketch more like humans do
Hybrid AI model crafts smooth, high-quality videos in seconds
Novel AI model inspired by neural dynamics from the brain

MIT CSAIL

Massachusetts Institute of Technology

Computer Science & Artificial Intelligence Laboratory

32 Vassar St, Cambridge MA 02139

  • Contact
  • Press Requests
  • Accessibility
MIT Schwarzman College of Computing