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.

MIT engineers developed AI frameworks to identify evidence-driven hypotheses that could advance biologically inspired materials.

An electronic stacking technique could exponentially increase the number of transistors on chips, enabling more efficient AI hardware.

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 “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.

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

Research from the MIT Center for Constructive Communication finds this effect occurs even when reward models are trained on factual data.

Using LLMs to convert machine-learning explanations into readable narratives could help users make better decisions about when to trust a model.

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