相关论文: VisMoDAl: Visual Analytics for Evaluating and Impr…

Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though existing methods try to deal with the cross-modal…

Extracting interpretable equations from observational datasets to describe complex natural phenomena is one of the core goals of artificial intelligence. This field is known as symbolic regression (SR). In recent years, Transformer-based…

Vision-Language Models (VLMs) map complex visual inputs to semantic spaces, but interpreting the cross-modal reasoning of VLMs currently relies on post-hoc explainers evaluated via unimodal perturbation metrics. We expose a limitation in…

Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due…

Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark…

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reasoning. However, most text-centered systems rely mainly on textual evidence, while…

Large language models (LLMs) have recently shown strong potential in vulnerability detection (VD). However, accurately detecting vulnerabilities in real-world repositories requires reasoning over complex contextual interactions. Existing…

Digital watermarking is essential for securing generated images from diffusion models. Accurate watermark evaluation is critical for algorithm development, yet existing methods have significant limitations: they lack a unified framework for…

Vision capabilities in vision large language models (VLLMs) have consistently lagged behind their linguistic capabilities. In particular, numerous benchmark studies have demonstrated that VLLMs struggle when fine-grained visual information…

Vision language models (VLMs) demonstrate impressive capabilities in visual question answering and image captioning, acting as a crucial link between visual and language models. However, existing open-source VLMs heavily rely on pretrained…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, while other investigations reveal difficulties in their ability…

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a persistent challenge. In this paper, we investigate…

Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models to infer outputs based on visual and textual context…

Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- and high-level language reasoning, such as semantics and…

Recent advances in vision-language pre-training (VLP) have demonstrated impressive performance in a range of vision-language (VL) tasks. However, there exist several challenges for measuring the community's progress in building general…

Large language models (LLMs) have increased interest in vision language models (VLMs), which process image-text pairs as input. Studies investigating the visual understanding ability of VLMs have been proposed, but such studies are still…

We introduce InterChart, a diagnostic benchmark that evaluates how well vision-language models (VLMs) reason across multiple related charts, a task central to real-world applications such as scientific reporting, financial analysis, and…

Current multimodal benchmarks often conflate reasoning with domain-specific knowledge, making it difficult to isolate and evaluate general reasoning abilities in non-expert settings. To address this, we introduce VisualPuzzles, a benchmark…