Large Language Models (LLMs) have shown promise in the autonomous driving sector,
particularly in generalization and interpretability. We introduce a unique objectlevel …

Significant progress has been achieved on the improvement and downstream usages of the
Contrastive Language-Image Pre-training (CLIP) vision-language model, while less …

Background: The existence of toxic conversations in open-source platforms can degrade
relationships among software developers and may negatively impact software product …

Motivated by biological evolution, this paper explains the rationality of Vision Transformer by
analogy with the proven practical evolutionary algorithm (EA) and derives that both have …

While Transformers have rapidly gained popularity in various computer vision applications
post-hoc explanations of their internal mechanisms remain largely unexplored. Vision …

We present a novel usage of Transformers to make image classification interpretable. Unlike
mainstream classifiers that wait until the last fully connected layer to incorporate class …

Despite their remarkable performance the explainability of Vision Transformers (ViTs)
remains a challenge. While forward attention-based token attribution techniques have …

Multitask learning is a popular approach to training high-performing neural networks with
improved generalization. In this paper, we propose a background class to achieve improved …

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-
trained Vision Transformer (ViT) models to downstream applications. While current PEFT …

Abstract To interpret Vision Transformers post-hoc explanations assign salience scores to
input pixels providing human-understandable heatmaps. However whether these …