Related papers: VecGlypher: Unified Vector Glyph Generation with L…

While Vision-language Models (VLMs) have demonstrated strong semantic capabilities, their ability to interpret the underlying geometric structure of visual information is less explored. Pictographic characters, which combine visual form…

Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating…

Recent advancements in Multimodal Large Language Models (MLLMs) have been utilizing Visual Prompt Generators (VPGs) to convert visual features into tokens that LLMs can recognize. This is achieved by training the VPGs on millions of…

Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. This restricts the development of autonomous computer…

Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of…

Designing fonts for languages with a large number of characters, such as Japanese and Chinese, is an extremely labor-intensive and time-consuming task. In this study, we addressed the problem of automatically generating Japanese typographic…

We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm:…

Vector graphic documents present visual elements in a resolution free, compact format and are often seen in creative applications. In this work, we attempt to learn a generative model of vector graphic documents. We define vector graphic…

Visual grounding is an essential capability of Visual Language Models (VLMs) to understand the real physical world. Previous state-of-the-art grounding visual language models usually have large model sizes, making them heavy for deployment…

Image vectorization is a process to convert a raster image into a scalable vector graphic format. Objective is to effectively remove the pixelization effect while representing boundaries of image by scaleable parameterized curves. We…

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…

3D vector graphics play a crucial role in various applications including 3D shape retrieval, conceptual design, and virtual reality interactions due to their ability to capture essential structural information with minimal representation.…

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

Vector quantization (VQ) transforms continuous image features into discrete representations, providing compressed, tokenized inputs for generative models. However, VQ-based frameworks suffer from several issues, such as non-smooth latent…

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still…

This paper introduces a new approach to extract and analyze vector data from technical drawings in PDF format. Our method involves converting PDF files into SVG format and creating a feature-rich graph representation, which captures the…

Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs. While RGNNs have been increasingly adopted in many real-world…

Accurately understanding complex visual information is crucial for visual language models (VLMs). Enhancing image resolution can improve visual perception capabilities, not only reducing hallucinations but also boosting performance in tasks…

Vision language models (VLMs) achieve unified modeling of images and text, enabling them to accomplish complex real-world tasks through perception, planning, and reasoning. Among these tasks, reasoning is particularly representative, with…

Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution…