145 citations · 336 across the 15 of their papers we have counts for
7 papers · 1 filter
Assay2Mol: large language model-based drug design using BioAssay context
Yifan Deng, Spencer S. Ericksen, Anthony Gitter
Scientific databases aggregate vast amounts of quantitative data alongside descriptive text. In biochemistry, molecule screening assays evaluate candidate molecules' functional res…
Imitating Language via Scalable Inverse Reinforcement Learning
Markus Wulfmeier, Michael Bloesch, Nino Vieillard +13
The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning…
BOND: Aligning LLMs with Best-of-N Distillation
Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot +17
Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-t…
RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning
Sabela Ramos, Sertan Girgin, Léonard Hussenot +9
We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (…
Hyperparameter Selection for Imitation Learning
Leonard Hussenot, Marcin Andrychowicz, Damien Vincent +11
We address the issue of tuning hyperparameters (HPs) for imitation learning algorithms in the context of continuous-control, when the underlying reward function of the demonstratin…
*-CFQ: Analyzing the Scalability of Machine Learning on a Compositional Task
Dmitry Tsarkov, Tibor Tihon, Nathan Scales +3
We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalabilit…
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
Daniel Keysers, Nathanael Schärli, Nathan Scales +11
State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this…