相关论文: Reasoning with Pixel-level Precision: QVLM Archite…

Spatial reasoning is a core component of human cognition, enabling individuals to perceive, comprehend, and interact with the physical world. It relies on a nuanced understanding of spatial structures and inter-object relationships, serving…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

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…

Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in…

Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason…

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…

In this paper, we propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference. Conventional quantization methods sequentially search the layer-wise rounding functions by…

Multimodal Large Language Models (MLLMs) encode images into visual tokens, aligning visual and textual signals within a shared latent space to facilitate crossmodal representation learning. The CLIP model is a widely adopted foundational…

Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this…

Vision language models (VLMs) are an exciting emerging class of language models (LMs) that have merged classic LM capabilities with those of image processing systems. However, the ways that these capabilities combine are not always…

Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of…

Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation…

Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric…

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However,…

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…

MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…

Counting serves as a simple but powerful test of a Large Vision-Language Model's (LVLM's) reasoning; it forces the model to identify each individual object and then add them all up. In this study, we investigate how LVLMs implement counting…

Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…