相关论文: Probing Vision-Language Understanding through the …

Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models, and are able to learn from and process multi-modal vision-text input. While modern VLMs perform well on a number of…

An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision encoders, resulting in large vision-language models (LVLMs).…

Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce. Recent open-source work like DeepSeek-R1 demonstrates…

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts…

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains…

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of…

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…

Understanding causal relationships across modalities is a core challenge for multimodal models operating in real-world environments. We introduce ISO-Bench, a benchmark for evaluating whether models can infer causal dependencies between…

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide…

Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide…

We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high…

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on…

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…

When visual evidence is ambiguous, vision models must decide whether to interpret face-like patterns as meaningful. Face pareidolia, the perception of faces in non-face objects, provides a controlled probe of this behavior. We introduce a…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

With deep neural models increasingly permeating our daily lives comes a need for transparent and comprehensible explanations of their decision-making. However, most explanation methods that have been developed so far are not intuitively…

Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual…