1
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the …
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown …
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining …
Counterfactual prediction under sequences of actions is a fundamental problem in decision-making. Existing methods in causal inference …
Compositionality, or the ability to combine familiar units like words into novel phrases and sentences, has been the focus of intense …
Semantic parsing is the task of producing a structured meaning representation for natural language utterances or questions. Recent …
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language tasks. In …
Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently …
We are interested in interactive agents that learn to coordinate, namely, a
builder – which performs actions but ignores the goal …
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the …