Berkeley BAIR

Berkeley BAIR proposes GRASP, a gradient-based planner for learned world models enabling longer-horizon planning via differentiable dynamics.

Berkeley BAIR develops scalable interaction identification methods to improve LLM interpretability and safety through feature/data attribution analysis.

Berkeley BAIR explores information-theoretic design of imaging systems for autonomous vehicles and medical diagnostics via learned reconstruction.

Berkeley BAIR introduces divide-and-conquer RL algorithm scaling to long horizons without temporal difference learning overhead.

Berkeley BAIR provides closed-form theory of word2vec learning dynamics, reducing representation learning to least-squares matrix factorization.

Berkeley BAIR develops whole-body egocentric video prediction conditioned on human pose for embodied AI applications.

Berkeley BAIR proposes StruQ and SecAlign to defend LLM apps against prompt injection via structured queries and preference optimization.

Berkeley BAIR's PLAID model generates proteins (sequence + 3D structure) via latent diffusion in AlphaFold2 latent space, enabling billion-scale training.

Berkeley BAIR deployed 100 RL-controlled autonomous vehicles on highway to reduce congestion and fuel consumption via flow-smoothing control.

Berkeley BAIR's Anthology conditions LLMs to consistent virtual personas via naturalistic backstories for representative behavioral diversity.