180 citations · 428 across the 11 of their papers we have counts for
7 papers · 1 filter
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
Alan Chan, Ben Bucknall, Herbie Bradley +1
Public release of the weights of pretrained foundation models, otherwise known as downloadable access \citep{solaiman_gradient_2023}, enables fine-tuning without the prohibitive ex…
Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
Joseph Suárez, Phillip Isola, Kyoung Whan Choe +15
Neural MMO 2.0 is a massively multi-agent environment for reinforcement learning research. The key feature of this new version is a flexible task system that allows users to define…
Quality-Diversity through AI Feedback
Herbie Bradley, Andrew Dai, Hannah Teufel +7
In many text-generation problems, users may prefer not only a single response, but a diverse range of high-quality outputs from which to choose. Quality-diversity (QD) search algor…
Challenges and Applications of Large Language Models
Jean Kaddour, Joshua Harris, Maximilian Mozes +3
Large Language Models (LLMs) went from non-existent to ubiquitous in the machine learning discourse within a few years. Due to the fast pace of the field, it is difficult to identi…
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Stella Biderman, Hailey Schoelkopf, Quentin Anthony +10
How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \textit{Py…
Reclaiming the Digital Commons: A Public Data Trust for Training Data
Alan Chan, Herbie Bradley, Nitarshan Rajkumar
Democratization of AI means not only that people can freely use AI, but also that people can collectively decide how AI is to be used. In particular, collective decision-making pow…
Language Model Crossover: Variation through Few-Shot Prompting
Elliot Meyerson, Mark J. Nelson, Herbie Bradley +4
This paper pursues the insight that language models naturally enable an intelligent variation operator similar in spirit to evolutionary crossover. In particular, language models o…