12 citations · 13 across the 4 of their papers we have counts for
4 papers · 1 filter
Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
Divyansh Pareek, Sewoong Oh, Simon S. Du
The success of modern multimodal representation learning relies on internet-scale datasets. Due to the low quality of a large fraction of raw web data, data curation has become a c…
Understanding the Gains from Repeated Self-Distillation
Divyansh Pareek, Simon S. Du, Sewoong Oh
Self-Distillation is a special type of knowledge distillation where the student model has the same architecture as the teacher model. Despite using the same architecture and the sa…
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
Divyansh Pareek, Andrej Risteski
Training and using modern neural-network based latent-variable generative models (like Variational Autoencoders) often require simultaneously training a generative direction along…
Finding Input Characterizations for Output Properties in ReLU Neural Networks
Saket Dingliwal, Divyansh Pareek, Jatin Arora
Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are being increasingly deployed in real-world safety-critical domains. Despite the widespread success, their co…