Machine Learning

Auto Added by WPeMatico

Moonshot AI Releases 𝑨𝒕𝒕𝒆𝒏𝒕𝒊𝒐𝒏 𝑹𝒆𝒔𝒊𝒅𝒖𝒂𝒍𝒔 to Replace Fixed Residual Mixing with Depth-Wise Attention for Better Scaling in Transformers

agentic ai, ai, AI (Artificial Intelligence), Artificial Intelligence, Editors Pick, Machine Learning, New Releases, Staff, Technology

Residual connections are one of the least questioned parts of modern Transformer design. In PreNorm architectures, each layer adds its output back into a running hidden state, which keeps optimization stable and allows deep models to train. Moonshot AI researchers argue that this standard mechanism also introduces a structural problem: all prior layer outputs are

Moonshot AI Releases 𝑨𝒕𝒕𝒆𝒏𝒕𝒊𝒐𝒏 𝑹𝒆𝒔𝒊𝒅𝒖𝒂𝒍𝒔 to Replace Fixed Residual Mixing with Depth-Wise Attention for Better Scaling in Transformers Read More »

Google AI Introduces ‘Groundsource’: A New Methodology that Uses Gemini Model to Transform Unstructured Global News into Actionable, Historical Data

ai, AI (Artificial Intelligence), AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Machine Learning, New Releases, Tech News, Technology

Google AI Research team recently released Groundsource, a new methodology that uses Gemini model to extract structured historical data from unstructured public news reports. The project addresses the lack of historical data for rapid-onset natural disasters. Its first output is an open-source dataset containing 2.6 million historical urban flash flood events across more than 150

Google AI Introduces ‘Groundsource’: A New Methodology that Uses Gemini Model to Transform Unstructured Global News into Actionable, Historical Data Read More »

How to Build an Autonomous Machine Learning Research Loop in Google Colab Using Andrej Karpathy’s AutoResearch Framework for Hyperparameter Discovery and Experiment Tracking

ai, AI (Artificial Intelligence), Artificial Intelligence, Editors Pick, Machine Learning, Staff, Technology, Tutorials

In this tutorial, we implement a Colab-ready version of the AutoResearch framework originally proposed by Andrej Karpathy. We build an automated experimentation pipeline that clones the AutoResearch repository, prepares a lightweight training environment, and runs a baseline experiment to establish initial performance metrics. We then create an automated research loop that programmatically edits the hyperparameters

How to Build an Autonomous Machine Learning Research Loop in Google Colab Using Andrej Karpathy’s AutoResearch Framework for Hyperparameter Discovery and Experiment Tracking Read More »

Can AI help predict which heart-failure patients will worsen within a year?

ai, AI (Artificial Intelligence), Artificial Intelligence, Computer science and technology, data, Electrical engineering and computer science (EECS), Harvard-MIT Health Sciences and Technology, Health care, Health sciences and technology, Jameel Clinic, Machine Learning, Medicine, MIT Schwarzman College of Computing, Research, Research Laboratory of Electronics, School of Engineering

Characterized by weakened or damaged heart musculature, heart failure results in the gradual buildup of fluid in a patient’s lungs, legs, feet, and other parts of the body. The condition is chronic and incurable, often leading to arrhythmias or sudden cardiac arrest. For many centuries, bloodletting and leeches were the treatment of choice, famously practiced

Can AI help predict which heart-failure patients will worsen within a year? Read More »

3 Questions: On the future of AI and the mathematical and physical sciences

ai, AI (Artificial Intelligence), Algorithms, Artificial Intelligence, Astronomy and astrophysics, Chemistry, Computer science and technology, data, Faculty, IDSS, Interview, Laboratory for Nuclear Science, Machine Learning, Materials science and engineering, Mathematics, MIT Schwarzman College of Computing, National Science Foundation (NSF), Physics, Research, School of Science

Curiosity-driven research has long sparked technological transformations. A century ago, curiosity about atoms led to quantum mechanics, and eventually the transistor at the heart of modern computing. Conversely, the steam engine was a practical breakthrough, but it took fundamental research in thermodynamics to fully harness its power. Today, artificial intelligence and science find themselves at a

3 Questions: On the future of AI and the mathematical and physical sciences Read More »

NVIDIA Releases Nemotron 3 Super: A 120B Parameter Open-Source Hybrid Mamba-Attention MoE Model Delivering 5x Higher Throughput for Agentic AI

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Staff, Technology

The gap between proprietary frontier models and highly transparent open-source models is closing faster than ever. NVIDIA has officially pulled the curtain back on Nemotron 3 Super, a staggering 120 billion parameter reasoning model engineered specifically for complex multi-agent applications. Released today, Nemotron 3 Super sits perfectly between the lightweight 30 billion parameter Nemotron 3

NVIDIA Releases Nemotron 3 Super: A 120B Parameter Open-Source Hybrid Mamba-Attention MoE Model Delivering 5x Higher Throughput for Agentic AI Read More »

A better method for planning complex visual tasks

Aeronautical and astronautical engineering, ai, AI (Artificial Intelligence), Algorithms, Artificial Intelligence, Computer science and technology, Computer vision, Laboratory for Information and Decision Systems (LIDS), Machine Learning, MIT Schwarzman College of Computing, MIT-IBM Watson AI Lab, Research, Robotics, School of Engineering

MIT researchers have developed a generative artificial intelligence-driven approach for planning long-term visual tasks, like robot navigation, that is about twice as effective as some existing techniques.Their method uses a specialized vision-language model to perceive the scenario in an image and simulate actions needed to reach a goal. Then a second model translates those simulations

A better method for planning complex visual tasks Read More »

3 Questions: Building predictive models to characterize tumor progression

ai, AI (Artificial Intelligence), Artificial Intelligence, Biology, Cancer, Computational biology, DNA, Evolution, Faculty, Genetics, Health sciences and technology, Institute for Medical Engineering and Science (IMES), Interview, Koch Institute, Machine Learning, Medicine, School of Science

Just as Darwin’s finches evolved in response to natural selection in order to endure, the cells that make up a cancerous tumor similarly counter selective pressures in order to survive, evolve, and spread. Tumors are, in fact, complex sets of cells with their own unique structure and ability to change. Today, artificial Intelligence and machine learning

3 Questions: Building predictive models to characterize tumor progression Read More »

How Joseph Paradiso’s sensing innovations bridge the arts, medicine, and ecology

ai, AI (Artificial Intelligence), Alumni/ae, Artificial Intelligence, Digital technology, Ecology, Electronics, Environment, Faculty, Health, Internet of things, Machine Learning, Media Lab, Medicine, Physics, Profile, School of Architecture and Planning, School of Science, Sensors, Space, Wearable sensors, Wireless

Joseph Paradiso thinks that the most engaging research questions usually span disciplines. Paradiso was trained as a physicist and completed his PhD in experimental high-energy physics at MIT in 1981. His father was a photographer and filmmaker working at MIT, MIT Lincoln Laboratory, and the MITRE Corporation, so he grew up in a house where artists, scientists,

How Joseph Paradiso’s sensing innovations bridge the arts, medicine, and ecology Read More »

How Much Training Data Do You Really Need for Machine Learning in 2026?

ai, AI (Artificial Intelligence), Artificial Intelligence, Data Collection, Machine Learning, Shaip Blogs

A successful machine learning model starts with high-quality training data. But one of the most common questions teams ask at the start of an AI project is: how much training data is enough? The honest answer is that there is no fixed number that works for every project. The amount of data you need depends

How Much Training Data Do You Really Need for Machine Learning in 2026? Read More »