BAIR Blog
8 stories
BAIR BlogResearchFrom CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction.
BAIR BlogResearchTeaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction Overview 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…
BAIR BlogResearchIntelligence is Free, Now What? 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.
BAIR BlogResearch2026 BAIR Graduate Showcase Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D.
BAIR BlogResearchAdaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling Overview 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…
BAIR BlogResearchGradient-based Planning for World Models at Longer Horizons GRASP 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…
BAIR BlogResearchIdentifying 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.
BAIR BlogResearchInformation-Driven Design of Imaging Systems An encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements.
Nothing matches this filter yet.