Search Results for author:
Found 4 papers, 2 papers with code
BridgeData V2: A Dataset for Robot Learning at Scale
By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods.
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
Our method achieves robust performance in the real world by learning an embedding from the labeled data that aligns language not to the goal image, but rather to the desired change between the start and goal images that the instruction corresponds to.
Neural Unsupervised Reconstruction of Protolanguage Word Forms
We evaluate our performance on the task of reconstructing Latin from a dataset of cognates across five Romance languages, achieving a notable reduction in edit distance from the target word forms compared to previous methods.
Understanding Game-Playing Agents with Natural Language Annotations
We present a new dataset containing 10K human-annotated games of Go and show how these natural language annotations can be used as a tool for model interpretability.
