Related papers: Enabling Stroke-Level Structural Analysis of Hiero…

In the last decade, the blossom of deep learning has witnessed the rapid development of scene text recognition. However, the recognition of low-resolution scene text images remains a challenge. Even though some super-resolution methods have…

Large Language Models (LLMs) have shown remarkable capabilities in processing various data structures, including graphs. While previous research has focused on developing textual encoding methods for graph representation, the emergence of…

Recent efforts leverage Large Language Models (LLMs) for modeling text-attributed graph structures in node classification tasks. These approaches describe graph structures for LLMs to understand or aggregate LLM-generated textual attribute…

Current Large Language Models (LLMs) for understanding proteins primarily treats amino acid sequences as a text modality. Meanwhile, Protein Language Models (PLMs), such as ESM-2, have learned massive sequential evolutionary knowledge from…

When reading a document, glancing at the spatial layout of a document is an initial step to understand it roughly. Traditional document layout analysis (DLA) methods, however, offer only a superficial parsing of documents, focusing on basic…

Large language models (LLMs) are gaining increasing attention for their capability to process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies demonstrate that LLMs obtain decent text classification…

The growing importance of textual and relational systems has driven interest in enhancing large language models (LLMs) for graph-structured data, particularly Text-Attributed Graphs (TAGs), where samples are represented by textual…

Representation learning on heterogeneous text-rich networks (HTRNs), which consist of multiple types of nodes and edges with each node associated with textual information, is essential for various real-world applications. Given the success…

Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\em semantic data processing}, where familiar data processing operators (e.g., map, reduce,…

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…

As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most…

Understanding large-scale, complex software systems is a major challenge for developers, who spend a significant portion of their time on program comprehension. Traditional tools such as static visualizations and reverse engineering…

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in…

Recently, data-centric AI methodology has been a dominant paradigm in single-cell transcriptomics analysis, which treats data representation rather than model complexity as the fundamental bottleneck. In the review of current studies,…

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…

Acute stroke demands prompt diagnosis and treatment to achieve optimal patient outcomes. However, the intricate and irregular nature of clinical data associated with acute stroke, particularly blood pressure (BP) measurements, presents…

We explore the capabilities of LVLMs and LLMs in deciphering rare scripts not encoded in Unicode. We introduce a novel approach to construct a multimodal dataset of linguistic puzzles involving such scripts, utilizing a tokenization method…

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when…

Large language models (LLMs), such as GPT4 and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs…