7 citations · 7 across the 3 of their papers we have counts for
4 papers
MoIN: Mixture of Introvert Experts to Upcycle an LLM
Ajinkya Tejankar, KL Navaneet, Ujjawal Panchal +2
The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to spl…
Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning
KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar +3
We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluste…
A Simple Baseline for Low-Budget Active Learning
Kossar Pourahmadi, Parsa Nooralinejad, Hamed Pirsiavash
Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested…
TaxoNN: A Light-Weight Accelerator for Deep Neural Network Training
Reza Hojabr, Kamyar Givaki, Kossar Pourahmadi +4
Emerging intelligent embedded devices rely on Deep Neural Networks (DNNs) to be able to interact with the real-world environment. This interaction comes with the ability to retrain…