3 papers
cs.RO2025
Uncertainty-aware Test-Time Training (UT) for Efficient On-the-fly Domain Adaptive Dense Regression
Uddeshya Upadhyay
Deep neural networks (DNNs) are increasingly being used in autonomous systems. However, DNNs do not generalize well to domain shift. Adapting to a continuously evolving environment…
cs.CV2025
Perceiving Beyond Language Priors: Enhancing Visual Comprehension and Attention in Multimodal Models
Aarti Ghatkesar, Ganesh Venkatesh
Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual inpu…
cs.LG2024
The Manifold Hypothesis for Gradient-Based Explanations
Sebastian Bordt, Uddeshya Upadhyay, Zeynep Akata +1
When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space…