相关论文: Can Language Models Understand Physical Concepts?

Vision-language models (VLMs) such as CLIP have shown promising performance on a variety of recognition tasks using the standard zero-shot classification procedure -- computing similarity between the query image and the embedded words for…

Multimodal Large Language Models (MLLMs) have remarkably progressed in analyzing and understanding images. Despite these advancements, accurately regressing values in charts remains an underexplored area for MLLMs. For visualization, how do…

Vision-language models (VLMs) hold promise for enhancing visualization tools, but effective human-AI collaboration hinges on a shared perceptual understanding of visual content. Prior studies assessed VLM visualization literacy through…

Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini,…

Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…

The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of…

We investigate the ability of Vision Language Models (VLMs) to perform visual perspective taking using a new set of visual tasks inspired by established human tests. Our approach leverages carefully controlled scenes in which a single…

Distributional semantic models capture word-level meaning that is useful in many natural language processing tasks and have even been shown to capture cognitive aspects of word meaning. The majority of these models are purely text based,…

To what extent can language alone give rise to complex concepts, or is embodied experience essential? Recent advancements in large language models (LLMs) offer fresh perspectives on this question. Although LLMs are trained on restricted…

In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remains an open question whether this alignment is superficial or…

The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

One of the main objectives in developing large vision-language models (LVLMs) is to engineer systems that can assist humans with multimodal tasks, including interpreting descriptions of perceptual experiences. A central phenomenon in this…

While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, existing benchmarks often rely on question-answering or multiple-choice formats. These protocols allow models to exploit…

Pre-trained vision-language models (VLMs) learn to align vision and language representations on large-scale datasets, where each image-text pair usually contains a bag of semantic concepts. However, existing open-vocabulary object detectors…

As Vision and Language models (VLMs) are reaching users across the globe, assessing their cultural understanding has become a critical challenge. In this paper, we introduce CROPE, a visual question answering benchmark designed to probe the…

Images can be described in terms of the objects they contain, or in terms of the types of scene or place that they instantiate. In this paper we address to what extent pretrained Vision and Language models can learn to align descriptions of…

Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-curated benchmark targeting three components of spatial understanding: depth-ordered…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…