Puzzling out climate change | MIT News
Shreyaa Raghavan’s journey into solving some of the world’s toughest challenges started with a simple love for puzzles. By high school, her knack for problem-solving naturally drew her to computer…
A Step by Step Guide to Build an Interactive Health Data Monitoring Tool Using Hugging Face Transformers and Open Source Model Bio_ClinicalBERT
In this tutorial, we will learn how to build an interactive health data monitoring tool using Hugging Face’s transformer models, Google Colab, and ipywidgets. We walk you through setting up…
Bridging philosophy and AI to explore computing ethics | MIT News
During a meeting of class 6.C40/24.C40 (Ethics of Computing), Professor Armando Solar-Lezama poses the same impossible question to his students that he often asks himself in the research he leads…
Limbic AI’s Generative AI–Enabled Therapy Support Tool Improves Cognitive Behavioral Therapy Outcomes
Recent advancements in generative AI are creating exciting new possibilities in healthcare, especially within mental health services, where patient engagement is often a significant challenge. A recent observational study published…
Gift from Sebastian Man ’79, SM ’80 supports MIT Stephen A. Schwarzman College of Computing building | MIT News
The MIT Stephen A. Schwarzman College of Computing has received substantial support for its striking new headquarters on Vassar Street in Cambridge, Massachusetts. A major gift from Sebastian Man ’79,…
Enhancing LLM Reasoning with Multi-Attempt Reinforcement Learning
Recent advancements in RL for LLMs, such as DeepSeek R1, have demonstrated that even simple question-answering tasks can significantly enhance reasoning capabilities. Traditional RL approaches for LLMs often rely on…
AI model deciphers the code in proteins that tells them where to go | MIT News
Proteins are the workhorses that keep our cells running, and there are many thousands of types of proteins in our cells, each performing a specialized function. Researchers have long known…
What if You Could Control How Long a Reasoning Model “Thinks”? CMU Researchers Introduce L1-1.5B: Reinforcement Learning Optimizes AI Thought Process
Reasoning language models have demonstrated the ability to enhance performance by generating longer chain-of-thought sequences during inference, effectively leveraging increased computation. However, a major limitation is the lack of control…
Like human brains, large language models reason about diverse data in a general way | MIT News
While early language models could only process text, contemporary large language models now perform highly diverse tasks on different types of data. For instance, LLMs can understand many languages, generate…
STORM (Spatiotemporal TOken Reduction for Multimodal LLMs): A Novel AI Architecture Incorporating a Dedicated Temporal Encoder between the Image Encoder and the LLM
Understanding videos with AI requires handling sequences of images efficiently. A major challenge in current video-based AI models is their inability to process videos as a continuous flow, missing important…