相关论文: Do Vision-Language Foundational models show Robust…

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in…

Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing "under" or "behind" relationships between only two objects, pose significant…

Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that…

Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…

Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with…

What distinguishes robust models from non-robust ones? While for ImageNet distribution shifts it has been shown that such differences in robustness can be traced back predominantly to differences in training data, so far it is not known…

Perception in the real world requires robustness to diverse viewing conditions. Existing approaches often rely on specialized architectures or training with predefined data augmentations, limiting adaptability. Taking inspiration from…

Visual translation tolerance refers to our capacity to recognize objects over a wide range of different retinal locations. Although translation is perhaps the simplest spatial transform that the visual system needs to cope with, the extent…

Earth observation foundation models have shown strong generalization across multiple Earth observation tasks, but their robustness under real-world perturbations remains underexplored. To bridge this gap, we introduce REOBench, the first…

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remains poorly understood. To bridge this gap, we perform a…

Vision-Language Models (VLMs) excel at complex visual tasks such as VQA and chart understanding, yet recent work suggests they struggle with simple perceptual tests. We present an evaluation of vision-language models' capacity for nonlocal…

Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is able to process various downstream tasks simultaneously.…

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…

As multimodal learning finds applications in a wide variety of high-stakes societal tasks, investigating their robustness becomes important. Existing work has focused on understanding the robustness of vision-and-language models to…

Can Visual Question Answering (VQA) systems perform just as well when deployed in the real world? Or are they susceptible to realistic corruption effects e.g. image blur, which can be detrimental in sensitive applications, such as medical…

Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations. Despite growing real-world deployment, existing evaluations rely almost exclusively on success rate, whether the…

The advent of Vision-Language Models (VLMs) in medical image analysis has the potential to help process multimodal inputs and increase performance over traditional inference methods. However, when considering the domain in which these…

Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\textit{generative VLMs}$ that are trained for next-word…

State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes,…