New model predicts a chemical reaction’s point of no return
Chemists could use this quick computational method to design more efficient reactions that yield useful compounds, from fuels to pharmaceuticals.
National Science Foundation (NSF)
“Periodic table of machine learning” could fuel AI discovery
Researchers have created a unifying framework that can help scientists combine existing ideas to improve AI models or create new ones.
Training LLMs to self-detoxify their language
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
Could LLMs help design our next medicines and materials?
A new method lets users ask, in plain language, for a new molecule with certain properties, and receive a detailed description of how to synthesize it.
AI tool generates high-quality images faster than state-of-the-art approaches
Researchers fuse the best of two popular methods to create an image generator that uses less energy and can run locally on a laptop or smartphone.
Validation technique could help scientists make more accurate forecasts
MIT researchers developed a new approach for assessing predictions with a spatial dimension, like forecasting weather or mapping air pollution.
User-friendly system can help developers build more efficient simulations and AI models
By automatically generating code that leverages two types of data redundancy, the system saves bandwidth, memory, and computation.
Toward video generative models of the molecular world
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.
MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures
With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly.
Researchers reduce bias in AI models while preserving or improving accuracy
A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.