1 code implementation • 17 Nov 2023 • Matthew Walmer, Rose Kanjirathinkal, Kai Sheng Tai, Keyur Muzumdar, Taipeng Tian, Abhinav Shrivastava
In this work, we advance the state-of-the-art for this area by re-examining the design of transformer architectures for video representation learning.
no code implementations • 27 Feb 2023 • Jordan Cotler, Kai Sheng Tai, Felipe Hernández, Blake Elias, David Sussillo
The specific model to be emulated is determined by a model embedding vector that the meta-model takes as input; these model embedding vectors constitute a manifold corresponding to the given population of models.
1 code implementation • 27 May 2022 • Kai Sheng Tai, Taipeng Tian, Ser-Nam Lim
We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity.
1 code implementation • 17 Feb 2021 • Kai Sheng Tai, Peter Bailis, Gregory Valiant
Self-training is a standard approach to semi-supervised learning where the learner's own predictions on unlabeled data are used as supervision during training.
3 code implementations • 25 Jan 2019 • Kai Sheng Tai, Peter Bailis, Gregory Valiant
How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network?
1 code implementation • 7 Nov 2017 • Kai Sheng Tai, Vatsal Sharan, Peter Bailis, Gregory Valiant
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model.
no code implementations • 25 Jun 2017 • Vatsal Sharan, Kai Sheng Tai, Peter Bailis, Gregory Valiant
What learning algorithms can be run directly on compressively-sensed data?
16 code implementations • IJCNLP 2015 • Kai Sheng Tai, Richard Socher, Christopher D. Manning
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks.
Ranked #1 on Semantic Similarity on SICK