190 citations · 378 across the 13 of their papers we have counts for
13 papers
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Eigen Attention: Attention in Low-Rank Space for KV Cache Compression
Utkarsh Saxena, Gobinda Saha, Sakshi Choudhary +1
Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has be…
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha +1
Label corruption, where training samples are mislabeled due to non-expert annotation or adversarial attacks, significantly degrades model performance. Acquiring large, perfectly la…
Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting
Sangamesh Kodge, Gobinda Saha, Kaushik Roy
Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retrainin…
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi +1
Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as t…
CoDeC: Communication-Efficient Decentralized Continual Learning
Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha +1
Training at the edge utilizes continuously evolving data generated at different locations. Privacy concerns prohibit the co-location of this spatially as well as temporally distrib…
Continual Learning with Scaled Gradient Projection
Gobinda Saha, Kaushik Roy
In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue…
Synthetic Dataset Generation for Privacy-Preserving Machine Learning
Efstathia Soufleri, Gobinda Saha, Kaushik Roy
Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vision, speech recognition, object detection, to name a few. The principal reason f…
Saliency Guided Experience Packing for Replay in Continual Learning
Gobinda Saha, Kaushik Roy
Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is…
Gradient Projection Memory for Continual Learning
Gobinda Saha, Isha Garg, Kaushik Roy
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial…
SPACE: Structured Compression and Sharing of Representational Space for Continual Learning
Gobinda Saha, Isha Garg, Aayush Ankit +1
Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned ab…
A Photonic In-Memory Computing primitive for Spiking Neural Networks using Phase-Change Materials
Indranil Chakraborty, Gobinda Saha, Kaushik Roy
Spiking Neural Networks (SNNs) offer an event-driven and more biologically realistic alternative to standard Artificial Neural Networks based on analog information processing. This…
Toward Fast Neural Computing using All-Photonic Phase Change Spiking Neurons
Indranil Chakraborty, Gobinda Saha, Abhronil Sengupta +1
The rapid growth of brain-inspired computing coupled with the inefficiencies in the CMOS implementations of neuromrphic systems has led to intense exploration of efficient hardware…