AI learns how vision and sound are connected, without human intervention
This new machine-learning model can match corresponding audio and visual data, which could someday help robots interact in the real world.
Hybrid AI model crafts smooth, high-quality videos in seconds
The CausVid generative AI tool uses a diffusion model to teach an autoregressive (frame-by-frame) system to rapidly produce stable, high-resolution videos.
AI-enabled translations initiative empowers Ukrainian learners with new skills
Ukrainian students and collaborators provide high-quality translations of MIT OpenCourseWare educational resources.
Combining next-token prediction and video diffusion in computer vision and robotics
A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.
Study: AI could lead to inconsistent outcomes in home surveillance
Researchers find large language models make inconsistent decisions about whether to call the police when analyzing surveillance videos.
Two MIT films nominated for New England Emmy Awards
Films produced by MIT Video Productions and the Department of Mechanical Engineering highlight some of MIT’s global conversations about the environment and climate change.
A creation story told through immersive technology
Multimedia artist Jackson 2bears reimagines the Haudenosaunee longhouse and creation story.
Looking for a specific action in a video? This AI-based method can find it for you
A new approach could streamline virtual training processes or aid clinicians in reviewing diagnostic videos.
Creating bespoke programming languages for efficient visual AI systems
Associate Professor Jonathan Ragan-Kelley optimizes how computer graphics and images are processed for the hardware of today and tomorrow.
Analyzing pathways to persuasion
When it comes to shaping political beliefs, MIT postdoc Chloe Wittenberg PhD ’23 finds video captivates, but might not beat text.
A system to keep cloud-based gamers in sync
By synchronizing media streams transmitted from the cloud to two devices, researchers could improve cloud gaming and AR/VR applications.
Two Lincoln Laboratory software products honored with national Excellence in Technology Transfer Awards
Cloud security and video forensics software have been transitioned to end users.
Merging storytelling and technology, “The Conquered” comes together in true MIT fashion
MIT professors collaborate at a whirlwind pace to create and stage a play inspired by advances in neurotechnology.
Mark Rober to deliver MIT’s 2023 Commencement address
The popular YouTuber, engineer, and inventor works to engage young people in science and technology while encouraging curiosity and resilience.
Video on the record
MIT’s inaugural Bearing Witness, Seeking Justice conference explores video’s role in the struggle over truth and civil liberties.