November 2025

Making fairness in LLMs observable, quantifiable, and governable A new evaluation pipeline called FiSCo uncovers hidden biases and offers an assessment framework that evolves alongside language models. Conversational AI Weijie Xu November 20, 10:23 AM November 20, 10:24 AM Researchers who build large language models have made major strides in developing reasoning systems that can perform well-defined coding and math tasks, where each problem has one right answer. But real-world, personal, and human-oriented questions will always resist a […]

Ver mais

Large language models (LLMs) like ChatGPT can write an essay or plan a menu almost instantly. But until recently, it was also easy to stump them. The models, which rely on language patterns to respond to users’ queries, often failed at math problems and were not good at complex reasoning. Suddenly, however, they’ve gotten a lot better at these things. A new generation of LLMs known as reasoning models are being trained to solve complex problems. Like humans, […]

Ver mais

Computer-Aided Design (CAD) is the go-to method for designing most of today’s physical products. Engineers use CAD to turn 2D sketches into 3D models that they can then test and refine before sending a final version to a production line. But the software is notoriously complicated to learn, with thousands of commands to choose from. To be truly proficient in the software takes a huge amount of time and practice. MIT engineers are looking to ease CAD’s learning […]

Ver mais

“We’re here to talk about really substantive changes, and we want you to be a participant in that,” said Desirée Plata, the School of Engineering Distinguished Professor of Climate and Energy in MIT’s Department of Civil and Environmental Engineering, at Energizing@MIT: the MIT Energy Initiative’s (MITEI) Annual Research Conference that was held on Sept. 9-10. Plata’s words resonated with the 150-plus participants from academia, industry, and government meeting in Cambridge for the conference, whose theme was “tackling emerging […]

Ver mais

TL;DR Synthetic data is widely used to train foundation models when data is scarce, sensitive, or costly to collect. This data enables progress in domains like medical imaging, tabular data, and code by expanding datasets while protecting privacy. Depending on the domain, different generation techniques, like Bayesian networks, GANs, diffusion models, and LLMs, can be used to generate synthetic data. Training foundation models at scale is constrained by data. Whether working with text, code, images, or multimodal inputs, […]

Ver mais

What can we learn about human intelligence by studying how machines “think?” Can we better understand ourselves if we better understand the artificial intelligence systems that are becoming a more significant part of our everyday lives? These questions may be deeply philosophical, but for Phillip Isola, finding the answers is as much about computation as it is about cogitation. Isola, the newly tenured associate professor in the Department of Electrical Engineering and Computer Science (EECS), studies the fundamental […]

Ver mais