104 citations · 209 across the 10 of their papers we have counts for
17 papers · 1 filter
Know Thy Student: Interactive Learning with Gaussian Processes
Rose E. Wang, Mike Wu, Noah Goodman
Learning often involves interaction between multiple agents. Human teacher-student settings best illustrate how interactions result in efficient knowledge passing where the teacher…
Temperature as Uncertainty in Contrastive Learning
Oliver Zhang, Mike Wu, Jasmine Bayrooti +1
Contrastive learning has demonstrated great capability to learn representations without annotations, even outperforming supervised baselines. However, it still lacks important prop…
Improving Compositionality of Neural Networks by Decoding Representations to Inputs
Mike Wu, Noah Goodman, Stefano Ermon
In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs toget…
A Simple Framework for Uncertainty in Contrastive Learning
Mike Wu, Noah Goodman
Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder wi…
Conditional Negative Sampling for Contrastive Learning of Visual Representations
Mike Wu, Milan Mosse, Chengxu Zhuang +2
Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between tw…
HarperValleyBank: A Domain-Specific Spoken Dialog Corpus
Mike Wu, Jonathan Nafziger, Anthony Scodary +1
We introduce HarperValleyBank, a free, public domain spoken dialog corpus. The data simulate simple consumer banking interactions, containing about 23 hours of audio from 1,446 hum…