To build a better AI helper, start by modeling the irrational behavior of humans
A new technique can be used to predict the actions of human or AI agents who behave suboptimally while working toward unknown goals.
New AI method captures uncertainty in medical images
By providing plausible label maps for one medical image, the Tyche machine-learning model could help clinicians and researchers capture crucial information.
A faster, better way to prevent an AI chatbot from giving toxic responses
Researchers create a curious machine-learning model that finds a wider variety of prompts for training a chatbot to avoid hateful or harmful output.
Large language models use a surprisingly simple mechanism to retrieve some stored knowledge
Researchers demonstrate a technique that can be used to probe a model to see what it knows about new subjects.
Researchers enhance peripheral vision in AI models
By enabling models to see the world more like humans do, the work could help improve driver safety and shed light on human behavior.
Dealing with the limitations of our noisy world
Tamara Broderick uses statistical approaches to understand and quantify the uncertainty that can affect study results.
New AI model could streamline operations in a robotic warehouse
By breaking an intractable problem into smaller chunks, a deep-learning technique identifies the optimal areas for thinning out traffic in a warehouse.
This tiny, tamper-proof ID tag can authenticate almost anything
MIT engineers developed a tag that can reveal with near-perfect accuracy whether an item is real or fake. The key is in the glue on the back of the tag.
A new way to let AI chatbots converse all day without crashing
Researchers developed a simple yet effective solution for a puzzling problem that can worsen the performance of large language models such as ChatGPT.
A flexible solution to help artists improve animation
This new method draws on 200-year-old geometric foundations to give artists control over the appearance of animated characters.