Biodiversity researchers tested vision systems on how well they could retrieve relevant nature images. More advanced models performed well on simple queries but struggled with more research-specific prompts.

Five MIT faculty and staff, along with five alumni, are honored for electrical engineering and computer science advances.

With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly.

Researchers at MIT, NYU, and UCLA develop an approach to help evaluate whether large language models like GPT-4 are equitable enough to be clinically viable for mental health support.

The MIT senior will pursue graduate studies in the UK at Cambridge University and Imperial College London.

Five MIT faculty members and two additional alumni are honored with fellowships to advance research on beneficial AI.

The “PRoC3S” method helps an LLM create a viable action plan by testing each step in a simulation. This strategy could eventually aid in-home robots to complete more ambiguous chore requests.

In a recent commentary, a team from MIT, Equality AI, and Boston University highlights the gaps in regulation for AI models and non-AI algorithms in health care.

A new technique identifies and removes the training examples that contribute most to a machine-learning model’s failures.

MIT CSAIL director and EECS professor named a co-recipient of the honor for her robotics research, which has expanded our understanding of what a robot can be.

Researchers develop “ContextCite,” an innovative method to track AI’s source attribution and detect potential misinformation.

First organized MIT delegation highlights the Institute's growing commitment to addressing climate change by showcasing research on biodiversity conservation, AI, and the role of local communities.

Researchers propose a simple fix to an existing technique that could help artists, designers, and engineers create better 3D models.

The Tree-D Fusion system integrates generative AI and genus-conditioned algorithms to create precise simulation-ready models of 600,000 existing urban trees across North America.

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.

Yiming Chen ’24, Wilhem Hector, Anushka Nair, and David Oluigbo will start postgraduate studies at Oxford next fall.

A new design tool uses UV and RGB lights to change the color and textures of everyday objects. The system could enable surfaces to display dynamic patterns, such as health data and fashion designs.

The new Tayebati Postdoctoral Fellowship Program will support leading postdocs to bring cutting-edge AI to bear on research in scientific discovery or music.

Inspired by large language models, researchers develop a training technique that pools diverse data to teach robots new skills.

“MouthIO” is an in-mouth device that users can digitally design and 3D print with integrated sensors and actuators to capture health data and interact with a computer or phone.

By allowing users to clearly see data referenced by a large language model, this tool speeds manual validation to help users spot AI errors.

A new method can train a neural network to sort corrupted data while anticipating next steps. It can make flexible plans for robots, generate high-quality video, and help AI agents navigate digital environments.

By using a 3D printer like an iron, researchers can precisely control the color, shade, and texture of fabricated objects, using only one material.

Associate Professor Julian Shun develops high-performance algorithms and frameworks for large-scale graph processing.

MIT CSAIL researchers created an AI-powered method for low-discrepancy sampling, which uniformly distributes data points to boost simulation accuracy.

New dataset of “illusory” faces reveals differences between human and algorithmic face detection, links to animal face recognition, and a formula predicting where people most often perceive faces.

“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.

“ScribblePrompt” is an interactive AI framework that can efficiently highlight anatomical structures across different medical scans, assisting medical workers to delineate regions of interest and abnormalities.

Computer scientist who specializes in database management systems joins the leadership of the Department of Electrical Engineering and Computer Science.

A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.


Building on a landmark algorithm, researchers propose a way to make a smaller and more noise-tolerant quantum factoring circuit for cryptography.

With extensive international outreach experience as a faculty member and program leader, Boning brings a spirit of curiosity and collaboration to his new role.

AI agents could soon become indistinguishable from humans online. Could “personhood credentials” protect people against digital imposters?

In controlled experiments, MIT CSAIL researchers discover simulations of reality developing deep within LLMs, indicating an understanding of language beyond simple mimicry.

A new algorithm helps robots practice skills like sweeping and placing objects, potentially helping them improve at important tasks in houses, hospitals, and factories.

CSAIL researchers introduce a novel approach allowing robots to be trained in simulations of scanned home environments, paving the way for customized household automation accessible to anyone.

Genomics and lab studies reveal numerous findings, including a key role for Reelin amid neuronal vulnerability, and for choline and antioxidants in sustaining cognition.

MAIA is a multimodal agent that can iteratively design experiments to better understand various components of AI systems.

Neural network controllers provide complex robots with stability guarantees, paving the way for the safer deployment of autonomous vehicles and industrial machines.

The approach could help engineers design more efficient energy-conversion systems and faster microelectronic devices, reducing waste heat.

New CSAIL research highlights how LLMs excel in familiar scenarios but struggle in novel ones, questioning their true reasoning abilities versus reliance on memorization.

This new tool offers an easier way for people to analyze complex tabular data.

Twelve faculty members have been granted tenure in six units across MIT’s School of Engineering.

These models, which can predict a patient’s race, gender, and age, seem to use those traits as shortcuts when making medical diagnoses.

The dedicated teacher and academic leader transformed research in computer architectures, parallel computing, and digital design, enabling faster and more efficient computation.

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.

Combining natural language and programming, the method enables LLMs to solve numerical, analytical, and language-based tasks transparently.

The method uses language-based inputs instead of costly visual data to direct a robot through a multistep navigation task.

DenseAV, developed at MIT, learns to parse and understand the meaning of language just by watching videos of people talking, with potential applications in multimedia search, language learning, and robotics.

With generative AI models, researchers combined robotics data from different sources to help robots learn better.