MIT scientists debut a generative AI model that could create molecules addressing hard-to-treat diseases

A recent study from MIT reveals that large language models (LLMs) often rely on grammatical shortcuts rather than domain knowledge when responding to queries. This reliance can lead to unexpected failures when LLMs are deployed in new tasks, raising concerns about their reliability and reasoning capabilities.

PrismSSL is a newly released Python library that consolidates various self-supervised learning methods across multiple modalities, including audio, vision, and graphs, into a single modular codebase. It allows users to easily install, configure, and run pretext training with minimal code, while also enabling the reproduction of benchmarks and extension of the framework with new methods.

The tensorflow-riemopt library has been introduced as a Python tool for geometric machine learning within TensorFlow, offering efficient implementations of neural network layers with manifold-constrained parameters and stochastic optimization algorithms for non-Euclidean spaces.