berkeley-artificial-intelligence-research-2437f2d3·2 events·first seen Aliases: Berkeley Artificial Intelligence Research, Berkeley Artificial Intelligence Research Lab
Berkeley Artificial Intelligence Research (BAIR) Lab published its 2026 graduate showcase, highlighting PhD completions across LLMs, robotics, AI safety, computer vision, and human-AI interaction. Notable placements include a graduate joining OpenAI as Member of Technical Staff (LLM reasoning), one joining Physical Intelligence (generalist vision/robotics), one joining Mistral AI as AI Scientist, and one becoming an Assistant Professor at UCLA. The cohort's research themes span test-time vs. pretraining scaling tradeoffs, LLM fairness and calibration, dexterous manipulation, and generative modeling for proteins.
Researchers from BAIR introduce SPEX (Spectral Explainer) and ProxySPEX, algorithms for identifying influential feature, data, and model-component interactions in LLMs at scale. The approach exploits sparsity, low-degreeness, and hierarchy properties to reframe interaction discovery as a sparse recovery problem using tools from signal processing and coding theory. ProxySPEX achieves comparable performance to SPEX with roughly 10x fewer ablations by leveraging hierarchical structure. The methods are evaluated on feature attribution (sentiment analysis), data attribution, and mechanistic interpretability tasks, outperforming marginal methods like LIME at long context lengths.