Training Diffusion Models with Reinforcement Learning replay Diffusion models have ...

Researchers at the University of Berkeley, California, developed an AI forecasting system to predict future events with similar accuracy to human ...

Rethinking the Role of PPO in RLHF TL;DR: In RLHF, there’s tension between the reward learning phase, which uses human preference in the ...

Goal Representations for Instruction Following A longstanding goal of the field of robot learning has been to create generalist agents ...

Asymmetric Certified Robustness via Feature-Convex Neural Networks TLDR: We propose the asymmetric certified robustness problem, which ...

The structure of Ghostbuster, our new state-of-the-art method for detecting AI-generated text. Large language models like ChatGPT ...

AI caught everyone’s attention in 2023 with Large Language Models (LLMs) that can be instructed to perform general tasks, such as ...

Every year, the Berkeley Artificial Intelligence Research (BAIR) Lab graduates some of the most talented and innovative minds in artificial ...

As computer vision researchers, we believe that every pixel can tell a story. However, there seems to be a writer’s block settling into ...

Join us in Atlanta on April 10th and explore the landscape of security workforce. We will explore the vision, benefits, and use cases of AI for ...