research
∙
10/23/2022
Tail Batch Sampling: Approximating Global Contrastive Losses as Optimization over Batch Assignments
Contrastive Learning has recently achieved state-of-the-art performance ...
share
research
∙
02/08/2022
CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations
Deriving multimodal representations of audio and lexical inputs is a cen...
research
∙
09/15/2021
Efficient Domain Adaptation of Language Models via Adaptive Tokenization
Contextual embedding-based language models trained on large data sets, s...
research
∙
06/05/2020
Filtered Inner Product Projection for Multilingual Embedding Alignment
Due to widespread interest in machine translation and transfer learning,...
research
∙
06/10/2019
Embedding Imputation with Grounded Language Information
Due to the ubiquitous use of embeddings as input representations for a w...
research
∙
12/12/2018