Related papers: GTMA: Dynamic Representation Optimization for OOD …

The zero-shot capabilities of Vision-Language Models (VLMs) have been widely leveraged to improve predictive performance. However, previous works on transductive or test-time adaptation (TTA) often make strong assumptions about the data…

Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation methods typically focus on refining representation from…

Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories. Nevertheless, there…

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling…

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Current robot autonomy struggles to operate beyond the assumed Operational Design Domain (ODD), the specific set of conditions and environments in which the system is designed to function, while the real-world is rife with uncertainties…

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Generative zero-shot learning (ZSL) synthesizes features for unseen classes, leveraging semantic conditions to transfer knowledge from seen classes. However, it also introduces two intrinsic challenges: (1) class-level attributes fails to…

Despite multiple efforts made towards robust machine learning (ML) models, their vulnerability to adversarial examples remains a challenging problem that calls for rethinking the defense strategy. In this paper, we take a step back and…

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed a variety of attack strategies that can successfully bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based…

Image-text matching (ITM) aims to address the fundamental challenge of aligning visual and textual modalities, which inherently differ in their representations, continuous, high-dimensional image features vs. discrete, structured text. We…

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-trained cross-modal…

Unsupervised domain adaptation (UDA) has proven to be very effective in transferring knowledge obtained from a source domain with labeled data to a target domain with unlabeled data. Owing to the lack of labeled data in the target domain…

Machine learning algorithms typically assume independent and identically distributed samples in training and at test time. Much work has shown that high-performing ML classifiers can degrade significantly and provide overly-confident, wrong…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Generalization remains a fundamental challenge in robotic manipulation. To tackle this challenge, recent Vision-Language-Action (VLA) models build policies on top of Vision-Language Models (VLMs), seeking to transfer their open-world…

Efficient trajectory planning in off-road terrains presents a formidable challenge for autonomous vehicles, often necessitating complex multi-step pipelines. However, traditional approaches exhibit limited adaptability in dynamic…