Stanford AI Lab Blog

DECEMBER 6, 2021

Linderman, David Sussillo Contact : jsmith14@stanford.edu Links: Paper | Website Keywords : recurrent neural networks, switching linear dynamical systems, interpretability, fixed points Compositional Transformers for Scene Generation Authors : Drew A. Smith, Scott W. Mel, Ben Sorscher, Alex H. Williams, Surya Ganguli, Lisa M.

Contact 40

Contact Learning Theory Authoring Offline 40

Stanford AI Lab Blog

APRIL 25, 2022

Manning, Jure Leskovec Contact : xikunz2@cs.stanford.edu Award nominations: Spotlight Links: Paper | Website Keywords : knowledge graph, question answering, language model, commonsense reasoning, graph neural networks, biomedical qa Fast Model Editing at Scale Authors : Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, Christopher D.

Contact 40

Contact Award Authoring Language 40

The AI Alignment Forum

FEBRUARY 20, 2025

Published on February 20, 2025 11:54 PM GMT TLDR: We made substantial progress in 2024: We published a series of papers that verify key predictions of Singular Learning Theory (SLT) [ 1 , 2 , 3 , 4 , 5 , 6 ]. The S4 correspondence in small language models. Alignment).

Technique 52

Technique Sample Structure Train 52

The AI Alignment Forum

FEBRUARY 7, 2025

In either of these settings, theres a chance that the LLMs will write messages that encode meaning beyond the natural language definitions of the words used. Externalizing reasoning: It could be safer to have much smaller language models which put more reasoning into natural language. and Mathew et al. Roger and Greenblatt ).

Research 52

Research Fund Open Technique 52

The AI Alignment Forum

MARCH 28, 2025

Daniel Filan (00:28:50): If people remember my singular learning theory episodes , theyll get mad at you for saying that quadratics are all there is, but its a decent approximation. (00:28:56): Whereas in the crosscoder paper, language modeling doesnt seem like the kind of thing that is going to be very symmetric.

Model 52

Model Network Training Train 52