Dust
Dust is a zeroth-order training method proposed by Q Labs in October 2026 for language transformers without backpropagation.
Explore AI Research through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of AI Research.
Showing 1-4 of 4 articles
Dust is a zeroth-order training method proposed by Q Labs in October 2026 for language transformers without backpropagation.
Intrinsic Distribution Matching (IDM) is a method for training image generators that use one or two generator evaluations.
LIMA, short for "Less Is More for Alignment," is a 2023 research paper by Chunting Zhou and colleagues at Meta AI, Carnegie Mellon University, the University of Southern California, and Tel Aviv University…
Weight-Space Programming is an approach in which a general-purpose large language model reads, interprets, edits or constructs another neural network's numerical weights in response to a natural-language goal