BAIR Blog
- BAIR at CoRL 2026BAIR Blog ·
The Conference on Robot Learning (CoRL) takes place November 9–12, 2026, in Austin, Texas.
- From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple SiliconBAIR Blog ·
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.
- Teaching LLMs to Update Beliefs for Efficient Long-Horizon InteractionBAIR Blog ·
.abbel-fig { display: block; text-align: center; margin: 2.4em 0; line-height: 1.4; max-width: 100%; } .abbel-fig img { display: block; margin: 0.65em auto 0; height: auto; max-width: 100%; } /*…
- Intelligence is Free, Now What? Data Systems for, of, and by AgentsBAIR Blog ·
... government of the people, by the people, for the people ... — Abraham Lincoln, Gettysburg Address (1863) The cost of AI is dropping rapidly.
- 2026 BAIR Graduate ShowcaseBAIR Blog ·
Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D.
- Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference ScalingBAIR Blog ·
.apr-fig { text-align: center; margin: 1.35em 0; line-height: 1.4; } .apr-fig--wide img { display: inline-block; width: 100%; max-width: 100%; height: auto; vertical-align: middle; }…
- Gradient-based Planning for World Models at Longer HorizonsBAIR Blog ·
.grasp-results-table table { font-size: 0.875rem; line-height: 1.35; width: 100%; } .grasp-results-table th, .grasp-results-table td { padding: 0.35rem 0.5rem; } /* Consistent whitespace between…
- Identifying Interactions at Scale for LLMsBAIR Blog ·
--> Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence.
- Information-Driven Design of Imaging SystemsBAIR Blog ·
An encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements.
- RL without TD learningBAIR Blog ·
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer .
- What exactly does word2vec learn?BAIR Blog ·
What exactly does word2vec learn, and how? Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task.