BAIR at CoRL 2026The Conference on Robot Learning (CoRL) takes place November 9–12, 2026, in Austin, Texas. BAIR faculty, postdocs and students will be presenting research at various sessions, including an Early Career Keynote from Professor Negar Mehr. SeeBRBAIR11/09 17:00
From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple SiliconFigure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction. We face a new epoch in computing. Hardware is changingBRBAIR07/29 17:00
Teaching LLMs to Update Beliefs for Efficient Long-Horizon InteractionOverview of ABBEL compared to traditional recursive summarization. Beliefs replace the full interaction history as the agent’s working context, and belief grading improves performance by supervising the contents of each belief state.. As taBRBAIR07/26 17:00
Intelligence is Free, Now What? <br> Data Systems for, of, and by Agents... government of the people, by the people, for the people ... — Abraham Lincoln, Gettysburg Address (1863) The cost of AI is dropping rapidly. GPT-4-class capabilities cost roughly $30 per million tokens in early 2023; today the samBRBAIR07/07 17:00
2026 BAIR Graduate ShowcaseCongratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D. graduates whose curiosity, creativity, and perseverance have pushed the frontiers of artBRBAIR07/01 17:00
Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference ScalingOverview of adaptive parallel reasoning. What if a reasoning model could decide for itself when to decompose and parallelize independent subtasks, how many concurrent threads to spawn, and how to coordinate them based on the problem at handBRBAIR05/08 17:00
Gradient-based Planning for World Models at Longer HorizonsGRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity direBRBAIR04/20 17:00
Identifying Interactions at Scale for LLMs--> Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpretability research aims to make the decision-making process morBRBAIR03/13 17:00
Information-Driven Design of Imaging SystemsAn encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements. Our information estimator uses only these noisy measurements and a noise model to quantify how well measurements distinguish objects. ManyBRBAIR01/10 17:00
RL without TD learningIn this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalabilitBRBAIR11/01 17:00