activity
20172026
most citedOn Detecting Adversarial Perturbations

220 citations · 277 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

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…

cs.LG2024

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…

cs.LG2021

Model-Free Risk-Sensitive Reinforcement Learning

Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch +4

We extend temporal-difference (TD) learning in order to obtain risk-sensitive, model-free reinforcement learning algorithms. This extension can be regarded as modification of the R…

cs.LG20217 cited

Shaking the foundations: delusions in sequence models for interaction and control

Pedro A. Ortega, Markus Kunesch, Grégoire Delétang +16

The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domai…

cs.LG201934 cited

Meta-learning of Sequential Strategies

Pedro A. Ortega, Jane X. Wang, Mark Rowland +21

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. O…

cs.LG2018

Sinkhorn AutoEncoders

Giorgio Patrini, Rianne van den Berg, Patrick Forré +5

Optimal transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show that minimizing the p-Wasserstein distance between the generator…