相关论文: Evaluating Vision-Language Models on Bistable Imag…

Vision-Language Models (VLMs) have demonstrated impressive capabilities across a range of tasks, yet concerns about their potential biases exist. This work investigates the extent to which prominent VLMs exhibit cultural biases by…

Contemporary knowledge-based systems increasingly rely on multilingual emotion identification to support intelligent decision-making, yet they face major challenges due to emotional ambiguity and incomplete supervision. Emotion recognition…

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

Vision-as-inverse-graphics, the concept of reconstructing images into editable programs, remains challenging for Vision-Language Models (VLMs), which inherently lack fine-grained spatial grounding in one-shot settings. To address this, we…

Recent vision-language (VL) models are powerful, but can they reliably distinguish "right" from "left"? We curate three new corpora to quantify model comprehension of such basic spatial relations. These tests isolate spatial reasoning more…

Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce…

This study investigates the extent to which the Visual Entailment (VE) task serves as a reliable probe of vision-language understanding in multimodal language models, using the LLaMA 3.2 11B Vision model as a test case. Beyond reporting…

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in understanding and generating content across various modalities, such as images and text. However, their interpretability remains a challenge, hindering…

The classic duck-rabbit illusion reveals that when visual evidence is ambiguous, the human brain must decide what it sees. But where exactly do human observers draw the line between ''duck'' and ''rabbit'', and do machine classifiers draw…

Human communication often relies on visual cues to resolve ambiguity. While humans can intuitively integrate these cues, AI systems often find it challenging to engage in sophisticated multimodal reasoning. We introduce VAGUE, a benchmark…

Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual…

Multimodal large language models (MLLMs) are changing how Blind and Low Vision (BLV) people access visual information. Unlike traditional visual interpretation tools that only provide descriptions, MLLM-enabled applications offer…

A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We…

This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the emotions evoked by images. Recent user studies report an…

The evolution of Large Vision-Language Models (LVLMs) has progressed from single to multi-image reasoning. Despite this advancement, our findings indicate that LVLMs struggle to robustly utilize information across multiple images, with…

Large language models (LLMs) have recently experienced remarkable progress, where the advent of multi-modal large language models (MLLMs) has endowed LLMs with visual capabilities, leading to impressive performances in various multi-modal…

Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

Vision-language models (VLMs) show promise as tools for inferring affect from visual stimuli at scale; it is not yet clear how closely their outputs align with human affective ratings. We benchmarked nine VLMs, ranging from state-of-the-art…

This paper offers a mini review of Visual Word Sense Disambiguation (VWSD), which is a multimodal extension of traditional Word Sense Disambiguation (WSD). VWSD helps tackle lexical ambiguity in vision-language tasks. While conventional WSD…