5 papers
Shared LoRA Subspaces for almost Strict Continual Learning
Prakhar Kaushik, Ankit Vaidya, Shravan Chaudhari +2
Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high c…
SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration
Zhimin Shao, Abhay Yadav, Rama Chellappa +1
Reliable image correspondences form the foundation of vision-based spatial perception, enabling recovery of 3D structure and camera poses. However, unconstrained feature matching a…
DiffRegCD: Integrated Registration and Change Detection with Diffusion Features
Seyedehanita Madani, Rama Chellappa, Vishal M. Patel
Change detection (CD) is fundamental to computer vision and remote sensing, supporting applications in environmental monitoring, disaster response, and urban development. Most CD m…
The Universal Weight Subspace Hypothesis
Prakhar Kaushik, Shravan Chaudhari, Ankit Vaidya +2
We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence…
Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding
Yutao Tang, Cheng Zhao, Gaurav Mittal +4
Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning. However, effectively tokenizing 3D scenes into holistic s…