activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers

Zachary Shinnick, Liangze Jiang, Hemanth Saratchandran +2

Transformers are remarkably versatile, suggesting the existence of generic inductive biases beneficial across modalities. In this work, we explore a new way to instil such biases i…

cs.CV2026

SineProject: Machine Unlearning for Stable Vision Language Alignment

Arpit Garg, Hemanth Saratchandran, Simon Lucey

Multimodal Large Language Models (MLLMs) increasingly need to forget specific knowledge such as unsafe or private information without requiring full retraining. However, existing u…

cs.CV2026

Weight Conditioning for Smooth Optimization of Neural Networks

Hemanth Saratchandran, Thomas X. Wang, Simon Lucey

In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between th…

cs.CV2026

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields

Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey

In the realm of computer vision, Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation. Despite the remarkable progress i…

cs.CV2025

Structured Initialization for Vision Transformers

Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran +1

Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating thi…

cs.CV2025

Enhancing Transformers Through Conditioned Embedded Tokens

Hemanth Saratchandran, Simon Lucey

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the at…