Ecologists find computer vision models’ blind spots in retrieving wildlife images
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.
Alex Shipps | MIT CSAIL •
mit
Dec. 20, 2024 • ~9 min
Dec. 20, 2024 • ~9 min
Study reveals AI chatbots can detect race, but racial bias reduces response empathy
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.
Alex Ouyang | Abdul Latif Jameel Clinic for Machine Learning in Health •
mit
Dec. 16, 2024 • ~6 min
Dec. 16, 2024 • ~6 min
Teaching a robot its limits, to complete open-ended tasks safely
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.
Alex Shipps | MIT CSAIL •
mit
Dec. 12, 2024 • ~6 min
Dec. 12, 2024 • ~6 min
/
89