Making AI-generated code more accurate in any language
A new technique automatically guides an LLM toward outputs that adhere to the rules of whatever programming language or other format is being used.
Programming
User-friendly system can help developers build more efficient simulations and AI models
By automatically generating code that leverages two types of data redundancy, the system saves bandwidth, memory, and computation.
MIT launches new Music Technology and Computation Graduate Program
The program will invite students to investigate new vistas at the intersection of music, computing, and technology.
LLMs develop their own understanding of reality as their language abilities improve
In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.
“They can see themselves shaping the world they live in”
Developed by MIT RAISE, the Day of AI curriculum empowers K-12 students to collaborate on local and global challenges using AI.
MIT researchers introduce generative AI for databases
This new tool offers an easier way for people to analyze complex tabular data.
Technique improves the reasoning capabilities of large language models
Combining natural language and programming, the method enables LLMs to solve numerical, analytical, and language-based tasks transparently.
The power of App Inventor: Democratizing possibilities for mobile applications
More than a decade since its launch, App Inventor recently hosted its 100 millionth project and registered its 20 millionth user. Now hosted by MIT, the app also supports experimenting…
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.