相关论文: PixFoundation: Are We Heading in the Right Directi…

Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an…

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving…

Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways:…

Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. However, existing benchmarks primarily evaluate the embodied…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, also lacking some basic visual…

Large language models (LLMs) have achieved state-of-the-art results in many natural language processing tasks. They have also demonstrated ability to adapt well to different tasks through zero-shot or few-shot settings. With the capability…

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical…

Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present. In this work, we systematically investigate whether these…

Visual Language Models (VLMs) have demonstrated impressive capabilities in visual grounding tasks. However, their effectiveness in the medical domain, particularly for abnormality detection and localization within medical images, remains…

In this paper, the LCV2 modular method is proposed for the Grounded Visual Question Answering task in the vision-language multimodal domain. This approach relies on a frozen large language model (LLM) as intermediate mediator between the…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability…

The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their…

Extending image-based Large Multimodal Models (LMMs) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMMs to videos either lack the grounding capabilities (e.g., VideoChat,…

Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and then fine-tuning on task-specific data, VLM in the remote…

Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures remain prone to multimodal hallucinations. This structural vulnerability stems from an…

Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views. We introduce m2sv, a…

Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models…

Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and…