220 citations · 424 across the 25 of their papers we have counts for
27 papers
A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
Davide Paglieri, Logan Cross, Tim Genewein +3
Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can als…
From AGI to ASI
Tim Genewein, Matija Franklin, Alexander Lerchner +11
Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI…
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Tim Genewein, Li Kevin Wenliang, Jordi Grau-Moya +3
Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the lit…
Why is prompting hard? Understanding prompts on binary sequence predictors
Li Kevin Wenliang, Anian Ruoss, Jordi Grau-Moya +2
Frontier models can be prompted or conditioned to do many tasks, but finding good prompts is not always easy, nor is understanding some performant prompts. We view prompting as fin…
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
Anian Ruoss, Fabio Pardo, Harris Chan +3
In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) a…
Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
David Heurtel-Depeiges, Anian Ruoss, Joel Veness +1
Foundation models are strong data compressors, but when accounting for their parameter size, their compression ratios are inferior to standard compression algorithms. Naively reduc…