In our current age of artificial intelligence, computers can generate their own “art” by way of […]
<!– –>Figure 1: CoarsenConf architecture. <!– (I) The encoder $q_phi(z| X, mathcal{R})$ takes the fine-grained (FG) […]
Figure 1: stepwise behavior in self-supervised learning. When training common SSL algorithms, we find that the […]
Training Diffusion Models with Reinforcement Learning replay Diffusion models have recently emerged as the de facto […]
Rethinking the Role of PPO in RLHF TL;DR: In RLHF, there’s tension between the reward learning […]
Goal Representations for Instruction Following <!– Figure title. Figure caption. This image is centered and set […]
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 […]
AI caught everyone’s attention in 2023 with Large Language Models (LLMs) that can be instructed to […]
Every year, the Berkeley Artificial Intelligence Research (BAIR) Lab graduates some of the most talented and […]