相关论文: White-Balance First, Adjust Later: Cross-Camera Co…

Vision-based quality assessment in additive manufacturing often requires dedicated machine learning models and application-specific datasets. However, data collection and model training can be expensive and time-consuming. In this paper, we…

With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs has become increasingly important. Existing VLMs predominantly digest and understand…

Vision-Language Models (VLMs) have attained exceptional success across multimodal tasks such as image captioning and visual question answering. However, their robustness under noisy conditions remains unfamiliar. In this study, we present a…

Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from rule-mapping failures. We study this behavior as semantic fixation: preserving a default…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

Recent research suggests that Vision Language Models (VLMs) often rely on inherent biases learned during training when responding to queries about visual properties of images. These biases are exacerbated when VLMs are asked highly specific…

Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, even though the visual change is obvious to humans. This…

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of…

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score…

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent…

Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a…

This paper presents ColorBlindnessEval, a novel benchmark designed to evaluate the robustness of Vision-Language Models (VLMs) in visually adversarial scenarios inspired by the Ishihara color blindness test. Our dataset comprises 500…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising…

While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising…

We present Stable-Layers, a reinforcement learning framework that eliminates the need for paired supervision by fine-tuning a pretrained layer decomposition model using only feedback from a vision-language model (VLM). Starting from…

Spelling correction from visual input poses unique challenges for vision language models (VLMs), as it requires not only detecting but also correcting textual errors directly within images. We present ReViCo (Real Visual Correction), the…

Large-scale Vision-Language Models (LVLMs) are being deployed in real-world settings that require visual inference. As capabilities improve, applications in navigation, education, and accessibility are becoming practical. These settings…