Related papers: CharTide: Data-Centric Chart-to-Code Generation vi…

Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \text{instruction}, \text{data}, \text{code} \rangle$…

Text documents with numerical values involved are widely used in various applications such as scientific research, economy, public health and journalism. However, it is difficult for readers to quickly interpret such data-involved texts and…

We propose a novel framework that leverages Visual Question Answering (VQA) models to automate the evaluation of LLM-generated data visualizations. Traditional evaluation methods often rely on human judgment, which is costly and unscalable,…

We introduce CHARTOM, a visual theory-of-mind benchmark designed to evaluate multimodal large language models' capability to understand and reason about misleading data visualizations though charts. CHARTOM consists of carefully designed…

Data visualizations like charts are fundamental tools for quantitative analysis and decision-making across fields, requiring accurate interpretation and mathematical reasoning. The emergence of Multimodal Large Language Models (MLLMs)…

Vision Language Models (VLMs) demonstrate promising chart comprehension capabilities. Yet, prior explorations of their visualization literacy have been limited to assessing their response correctness and fail to explore their internal…

Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced…

Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various chart understanding tasks. However, the sheer size of these…

Despite the ubiquity of visualization examples published on the web, retargeting existing custom chart implementations to new datasets remains difficult, time-intensive, and tedious. The adaptation process assumes author familiarity with…

Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF)…

Although multimodal large language models (MLLMs) show promise in generating chart rendering code, editing charts via code presents a greater challenge. This task demands MLLMs to integrate chart understanding and reasoning capacities,…

Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets. However, scaling SFT data alone is inefficient and…

Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large language models (MLLMs) like GPT-4o have shown promise in…

While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-rich images and structured output generation remains…

Large vision-language models (LVLMs) struggle to reliably detect visual primitives in charts and align them with semantic representations, which severely limits their performance on complex visual reasoning. This lack of perceptual…

Recently, the introduction of Chain-of-Thought (CoT) has largely improved the generation ability of unified models. However, it is observed that the current thinking process during generation mainly focuses on the text consistency with the…

While Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities for reasoning and self-correction at the textual level, these strengths provide minimal benefits for complex tasks centered on visual perception, such as…

Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses…

Large Language Models (LLMs) can perform chart question-answering tasks but often generate unverified hallucinated responses. Existing answer attribution methods struggle to ground responses in source charts due to limited visual-semantic…

Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with high information density (HID) charts characterized by multiple subplots, legends, and…