Traditional computational approaches to design chemical species are limited by the need to
compute properties for a vast number of candidates, eg, by discriminative modeling …

The current development in deep learning is witnessing an exponential transition into
automation applications. This automation transition can provide a promising framework for …

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems
to align with human goals. RLHF has emerged as the central method used to finetune state …

Knowledge Distillation (KD) is a promising technique for reducing the high computational
demand of large language models (LLMs). However, previous KD methods are primarily …

We present a framework for robot skill acquisition, which 1) efficiently scale up data
generation of language-labelled robot data and 2) effectively distills this data down into a …

Recent improvements in conditional generative modeling have made it possible to generate
high-quality images from language descriptions alone. We investigate whether these …

Nowadays, open-source large language models like LLaMA have emerged. Recent
developments have incorporated supervised fine-tuning (SFT) and reinforcement learning …

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization
from existing datasets followed by fast online fine-tuning with limited interaction. However …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Reward and representation learning are two long-standing challenges for learning an
expanding set of robot manipulation skills from sensory observations. Given the inherent …