3 Questions: Modeling adversarial intelligence to exploit AI’s security vulnerabilities
MIT CSAIL Principal Research Scientist Una-May O’Reilly discusses how she develops agents that reveal AI models’ security weaknesses before hackers do.
MIT CSAIL Principal Research Scientist Una-May O’Reilly discusses how she develops agents that reveal AI models’ security weaknesses before hackers do.
Starting with a single frame in a simulation, a new system uses generative AI to emulate the dynamics of molecules, connecting static molecular structures and developing blurry pictures into videos.
Inspired by the mechanics of the human vocal tract, a new AI model can produce and understand vocal imitations of everyday sounds. The method could help build new sonic interfaces for entertainment and education.
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.
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 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.
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.
“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.
A new algorithm solves complicated partial differential equations by breaking them down into simpler problems, potentially guiding computer graphics and geometry processing.