From physics to generative AI: An AI model for advanced pattern generation
Inspired by physics, a new generative model PFGM++ outperforms diffusion models in image generation.
Download RSS feed: News Articles / In the Media / Audio
Inspired by physics, a new generative model PFGM++ outperforms diffusion models in image generation.
The program supports “outstanding theoretical scientists.”
Co-directors Youssef Marzouk and Nicolas Hadjiconstantinou describe how the standalone degree aims to train students in cross-cutting aspects of computational science and engineering.
The advance brings quantum error correction a step closer to reality.
Professor and two additional MIT affiliates honored for influential work on optical coherence tomography, which allows rapid detection of retinal disease, among other applications.
The MIT and Accenture Convergence Initiative for Industry and Technology announces new graduate fellows.
The 27 finalists — representing every school at MIT — will explore the technology’s impact on democracy, education, sustainability, communications, and much more.
Sharmi Shah ’23 pursued Course 2-A/6, a customizable degree path that combines mechanical engineering with computer science and electrical engineering.
Researchers use multiple AI models to collaborate, debate, and improve their reasoning abilities to advance the performance of LLMs while increasing accountability and factual accuracy.
Brad Pentelute and his lab compel the anthrax delivery system to deliver antibody and peptide variants into cells to treat cancer.
With Style2Fab, makers can rapidly customize models of 3D-printable objects, such as assistive devices, without hampering their functionality.
Although computer scientists may initially treat data bias and error as a nuisance, researchers argue it’s a hidden treasure trove for reflecting societal values.
Researchers use synthetic data to improve a model’s ability to grasp conceptual information, which could enhance automatic captioning and question-answering systems.
The system could improve image quality in video streaming or help autonomous vehicles identify road hazards in real-time.
“Lightning” system connects photons to the electronic components of computers using a novel abstraction, creating the first photonic computing prototype to serve real-time machine-learning inference requests.