Aspen K Hopkins — accepted AI-conference papers

2024

Position: On the Societal Impact of Open Foundation Models

Sayash Kapoor, Rishi Bommasani, Kevin Klyman, Shayne Longpre, Ashwin Ramaswami, Peter Cihon +19

ICML 2024oral

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on *open* foundation models, defined here as those with broadly available model weights (e.g., Llama 3, Stable Diffusion XL). We identify five distincti…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg

ICLR 2023top-5%

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this q…

Cited by 512 Source ↗PDF ↗code ↗Scholar ↗