📰 BAIR Blog

<meta name="description" conte

--> <meta name="keywords" content="Long Horizon, LLM training, Summarization, Efficient Context Representation, Conte

<meta name="description" content=

Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.D. graduate

<meta name="description" content="What if a reas

<meta name="description" content="GRASP is a new gradient-based planner for learned dynamics (a world model) th

<p style="text-align:center

<!-- These are comments in HTML. The above header text is needed to format the title, authors, etc. The "information-driven-imaging" is the representative image

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: <strong

What exactly does <code c

.modal { display: none; position: fixed; z-index: 9999; padding-top: 50px; left: 0; top: 0; width: 100%; height: 100%; overflow: auto; background-color: rgba(0,

<meta name="

<!-

<meta name="author" content="Nathan Li

<!-- These are comments in HTML. The above header text is needed to format the title, authors, etc. The "example_post" is an example representative image (not G

<!-- These are comments in HTML. The above header text is needed to format the title, authors, etc. The "example_post" is an example representative image (not G