Researchers discover a shortcoming that makes LLMs less reliable
Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.
Large language models can learn to mistakenly link certain sentence patterns with specific topics — and may then repeat these patterns instead of reasoning.
The coding framework uses modular concepts and simple synchronization rules to make software clearer, safer, and easier for LLMs to generate.
Researchers find that design elements of data visualizations influence viewers’ assumptions about the source of the information and its trustworthiness.
To reduce waste, the Refashion program helps users create outlines for adaptable clothing, such as pants that can be reconfigured into a dress. Each component of these pieces can be replaced, rearranged, or restyled.
Optimized for generative AI, TX-GAIN is driving innovation in biodefense, materials discovery, cybersecurity, and other areas of research and development.
By enabling users to easily create social apps that serve communities’ needs, the Graffiti framework aims to promote healthier online interactions.
The FabObscura system helps users design and print barrier-grid animations without electronics, and can help produce dynamic household, workplace, and artistic objects.
Balancing automation and agency, Associate Professor Arvind Satyanarayan develops interactive data visualizations that amplify human creativity and cognition.
You can adjust the frequency range of this durable, inexpensive antenna by squeezing or stretching its structure.
Four new professors join the Department of Architecture and MIT Media Lab.
The AI-enabled platform serves as a hub for MIT’s lifelong learning opportunities.
A team of researchers has mapped the challenges of AI in software development, and outlined a research agenda to move the field forward.
From the classroom to expanding research opportunities, students at MIT Music Technology use design to push the frontier of digital instruments and software for human expression and empowerment.
Researchers find nonclinical information in patient messages — like typos, extra white space, and colorful language — reduces the accuracy of an AI model.
Presentations targeted high-impact intersections of AI and other areas, such as health care, business, and education.