3 papers
cs.CV2025
HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer
Mohammad Helal Uddin, Liam Seymour, Sabur Baidya
Vision Transformers (ViTs) deliver state-of-the-art accuracy but their quadratic attention cost and redundant computations severely hinder deployment on latency and resource-constr…
cs.LG2025
CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems
Mohammad Helal Uddin, Sai Krishna Ghanta, Liam Seymour +1
Deep learning algorithms are becoming an essential component of many artificial intelligence (AI) driven applications, many of which run on resource-constrained and energy-constrai…
cs.LG2024
Large Language Models on Small Resource-Constrained Systems: Performance Characterization, Analysis and Trade-offs
Liam Seymour, Basar Kutukcu, Sabur Baidya
Generative AI like the Large Language Models (LLMs) has become more available for the general consumer in recent years. Publicly available services, e.g., ChatGPT, perform token ge…