Related papers: VectorGym: A Multitask Benchmark for SVG Code Gene…

General SVG modeling remains challenging due to fragmented datasets, limited transferability of methods across tasks, and the difficulty of handling structural complexity. In response, we leverage the strong transfer and generalization…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limitations when engaging with visual graphs. To study the…

In the field of computer graphics, the use of vector graphics, particularly Scalable Vector Graphics (SVG), represents a notable development from traditional pixel-based imagery. SVGs, with their XML-based format, are distinct in their…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects,…

This paper presents VQ-SGen, a novel algorithm for high-quality creative sketch generation. Recent approaches have framed the task as pixel-based generation either as a whole or part-by-part, neglecting the intrinsic and contextual…

Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics…

Scene Graph Generation (SGG) encodes visual relationships between objects in images as graph structures. Thanks to the advances of Vision-Language Models (VLMs), the task of Open-Vocabulary SGG has been recently proposed where models are…

Recent vision-language model (VLM)-based approaches have achieved impressive results on SVG generation. However, because they generate only text and lack visual signals during decoding, they often struggle with complex semantics and fail to…

We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with complex motions: LLM-based code synthesis fails to express fine,…

Automated data visualization plays a crucial role in simplifying data interpretation, enhancing decision-making, and improving efficiency. While large language models (LLMs) have shown promise in generating visualizations from natural…

Hand-drawn sketches are a natural and efficient medium for capturing and conveying ideas. Despite significant advancements in controllable natural image generation, translating freehand sketches into structured, machine-readable diagrams…

Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable…

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider…

Vector graphics are widely used to represent fonts, logos, digital artworks, and graphic designs. But, while a vast body of work has focused on generative algorithms for raster images, only a handful of options exists for vector graphics.…

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

We propose VRGym, a virtual reality testbed for realistic human-robot interaction. Different from existing toolkits and virtual reality environments, the VRGym emphasizes on building and training both physical and interactive agents for…

The remarkable progress of Multi-modal Large Language Models (MLLMs) has attracted significant attention due to their superior performance in visual contexts. However, their capabilities in turning visual figure to executable code, have not…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…