Can robots learn from machine dreams?
MIT CSAIL researchers used AI-generated images to train a robot dog in parkour, without real-world data. Their LucidSim system demonstrates generative AI's potential for creating robotics training data.
MIT-IBM Watson AI Lab
3 Questions: Inverting the problem of design
MIT and IBM researchers are creating linkage mechanisms to innovate human-AI kinematic engineering.
Enhancing LLM collaboration for smarter, more efficient solutions
“Co-LLM” algorithm helps a general-purpose AI model collaborate with an expert large language model by combining the best parts of both answers, leading to more factual responses.
A framework for solving parabolic partial differential equations
A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.
Method prevents an AI model from being overconfident about wrong answers
More efficient than other approaches, the “Thermometer” technique could help someone know when they should trust a large language model.
MIT researchers advance automated interpretability in AI models
MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.
How to assess a general-purpose AI model’s reliability before it’s deployed
A new technique enables users to compare several large models and choose the one that works best for their task.
Reasoning skills of large language models are often overestimated
New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.
Understanding the visual knowledge of language models
LLMs trained primarily on text can generate complex visual concepts through code with self-correction. Researchers used these illustrations to train an image-free computer vision system to recognize real photos.
Researchers use large language models to help robots navigate
The method uses language-based inputs instead of costly visual data to direct a robot through a multistep navigation task.
Looking for a specific action in a video? This AI-based method can find it for you
A new approach could streamline virtual training processes or aid clinicians in reviewing diagnostic videos.
Using ideas from game theory to improve the reliability of language models
A new “consensus game,” developed by MIT CSAIL researchers, elevates AI’s text comprehension and generation skills.
Creating bespoke programming languages for efficient visual AI systems
Associate Professor Jonathan Ragan-Kelley optimizes how computer graphics and images are processed for the hardware of today and tomorrow.
Natural language boosts LLM performance in coding, planning, and robotics
Three neurosymbolic methods help language models find better abstractions within natural language, then use those representations to execute complex tasks.
Mapping the brain pathways of visual memorability
For the first time, researchers use a combination of MEG and fMRI to map the spatio-temporal human brain dynamics of a visual image being recognized.