Starting with a single frame in a simulation, a new system uses generative AI to emulate the dynamics of molecules, connecting static molecular structures and developing blurry pictures into videos.

Machine-learning models let neuroscientists study the impact of auditory processing on real-world hearing.

With their recently-developed neural network architecture, MIT researchers can wring more information out of electronic structure calculations.

Inspired by the mechanics of the human vocal tract, a new AI model can produce and understand vocal imitations of everyday sounds. The method could help build new sonic interfaces for entertainment and education.

Biodiversity researchers tested vision systems on how well they could retrieve relevant nature images. More advanced models performed well on simple queries but struggled with more research-specific prompts.

MIT engineers developed AI frameworks to identify evidence-driven hypotheses that could advance biologically inspired materials.

With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly.

The “PRoC3S” method helps an LLM create a viable action plan by testing each step in a simulation. This strategy could eventually aid in-home robots to complete more ambiguous chore requests.

A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.

Research from the MIT Center for Constructive Communication finds this effect occurs even when reward models are trained on factual data.