Researchers teach LLMs to solve complex planning challenges
This new framework leverages a model’s reasoning abilities to create a “smart assistant” that finds the optimal solution to multistep problems.
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.
Robotic helper making mistakes? Just nudge it in the right direction
New research could allow a person to correct a robot’s actions in real-time, using the kind of feedback they’d give another human.
Like human brains, large language models reason about diverse data in a general way
A new study shows LLMs represent different data types based on their underlying meaning and reason about data in their dominant language.
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.
New training approach could help AI agents perform better in uncertain conditions
Sometimes, it might be better to train a robot in an environment that’s different from the one where it will be deployed.
Explained: Generative AI’s environmental impact
Rapid development and deployment of powerful generative AI models comes with environmental consequences, including increased electricity demand and water consumption.
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.