Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting.
While visual prompts offer a lightweight method of input-space adaptation for large-scale …

Robustness of deep learning segmentation models is crucial for their safe incorporation into
clinical practice. However, these models can falter when faced with distributional changes …

Large-scale language models achieved state-of-the-art performance over a number of
language tasks. However, they fail on adversarial language examples, which are sentences …

In autonomous driving, precise perception of surrounding objects is crucial for ensuring
safety. To this end, many advanced object detection models have been developed using …

Many machine learning methods operate by inverting a neural network at inference time,
which has become a popular technique for solving inverse problems in computer vision …

Group equivariance is a strong inductive bias useful in a wide range of deep learning tasks.
However, constructing efficient equivariant networks for general groups and domains is …

Self Supervised Learning (SSL) has emerged as a powerful paradigm to tackle data
landscapes with absence of human supervision. The ability to learn meaningful tasks …

Recent advancements in artificial intelligence have highlighted the strengths of large
pretrained models across diverse applications. However, these models often struggle with …