6 citations · 13 across the 6 of their papers we have counts for
8 papers
On the Importance of Calibration in Semi-supervised Learning
Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj +5
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency…
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo +7
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between…
Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications
Matthew Khoury, Rumen Dangovski, Longwu Ou +3
Deep neural networks have become the standard approach to building reliable Natural Language Processing (NLP) applications, ranging from Neural Machine Translation (NMT) to dialogu…
Contextualizing Enhances Gradient Based Meta Learning
Evan Vogelbaum, Rumen Dangovski, Li Jing +1
Meta learning methods have found success when applied to few shot classification problems, in which they quickly adapt to a small number of labeled examples. Prototypical represent…
WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
Li Jing, Rumen Dangovski, Marin Soljacic
We present a logarithmic-scale efficient convolutional neural network architecture for edge devices, named WaveletNet. Our model is based on the well-known depthwise convolution, a…
Shaping Long-lived Electron Wavepackets for Customizable Optical Spectra
Rumen Dangovski, Nicholas Rivera, Marin Soljacic +1
Electrons in atoms and molecules are versatile physical systems covering a vast range of light-matter interactions, enabling the physics of Rydberg states, photon-photon bound stat…