Related papers: Semantic Document Derendering: SVG Reconstruction …

Text as signs, labels, or instructions is a critical element of real-world scenes as they can convey important contextual information. 3D representations such as 3D Gaussian Splatting (3DGS) struggle to preserve fine-grained text details,…

Generating structured, editable diagrams remains a significant challenge for contemporary large language models, despite their proficiency in general-purpose vector code generation. The primary difficulty lies in the structural fragility of…

Retrieval-Augmented Generation (RAG) systems have become a dominant approach to augment large language models (LLMs) with external knowledge. However, existing vector database (VecDB) retrieval pipelines rely on flat or single-resolution…

In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods…

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Large language models (LLMs) have recently shown strong potential for Automated Program Repair (APR), yet most existing approaches remain unimodal and fail to leverage the rich diagnostic signals contained in visual artifacts such as…

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…

Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved…

Document classification is a task of assigning a new unclassified document to one of the predefined set of classes. The content based document classification uses the content of the document with some weighting criteria to assign it to one…

Document dewarping aims to rectify deformations in photographic document images, thus improving text readability, which has attracted much attention and made great progress, but it is still challenging to preserve document structures. Given…

We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based…

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…

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…

Shadow detection is commonly formulated as a vision-driven dense prediction problem, where models rely primarily on pixel-wise visual supervision to distinguish shadows from non-shadow regions. However, this formulation can become…

Disentangled representation learning remains challenging as the underlying factors of variation in the data do not naturally exist. The inherent complexity of real-world data makes it unfeasible to exhaustively enumerate and encapsulate all…

Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities. The visual cues offered by their complex layouts play a…

Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models…