Synthetic imagery sets new bar in AI training efficiency
MIT CSAIL researchers innovate with synthetic imagery to train AI, paving the way for more efficient and bias-reduced machine learning.
This 3D printer can watch itself fabricate objects
Computer vision enables contact-free 3D printing, letting engineers print with high-performance materials they couldn’t use before.
Using language to give robots a better grasp of an open-ended world
By blending 2D images with foundation models to build 3D feature fields, a new MIT method helps robots understand and manipulate nearby objects with open-ended language prompts.
To excel at engineering design, generative AI must learn to innovate, study finds
AI models that prioritize similarity falter when asked to design something completely new.
New tools are available to help reduce the energy that AI models devour
Amid the race to make AI bigger and better, Lincoln Laboratory is developing ways to reduce power, train efficiently, and make energy use transparent.
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.
Multi-AI collaboration helps reasoning and factual accuracy in large language models
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.
A pose-mapping technique could remotely evaluate patients with cerebral palsy
The machine-learning method works on most mobile devices and could be expanded to assess other motor disorders outside of the doctor’s office.
Helping computer vision and language models understand what they see
Researchers use synthetic data to improve a model’s ability to grasp conceptual information, which could enhance automatic captioning and question-answering systems.
AI model speeds up high-resolution computer vision
The system could improve image quality in video streaming or help autonomous vehicles identify road hazards in real-time.
MIT researchers combine deep learning and physics to fix motion-corrupted MRI scans
The challenge involves more than just a blurry JPEG. Fixing motion artifacts in medical imaging requires a more sophisticated approach.
Using AI to protect against AI image manipulation
“PhotoGuard,” developed by MIT CSAIL researchers, prevents unauthorized image manipulation, safeguarding authenticity in the era of advanced generative models.
A new dataset of Arctic images will spur artificial intelligence research
The dataset, being collected as part of a US Coast Guard science mission, will be released open source to help advance naval mission planning and climate change studies.
When computer vision works more like a brain, it sees more like people do
Training artificial neural networks with data from real brains can make computer vision more robust.
Computer vision system marries image recognition and generation
MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.