Related papers: TypeScript Repository Indexing for Code Agent Retr…
Recently, the emerging graph Transformers have made significant advancements for node classification on graphs. In most graph Transformers, a crucial step involves transforming the input graph into token sequences as the model input,…
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…
Code generation aims to produce code that fulfills requirements written in natural languages automatically. Large language Models (LLMs) like ChatGPT have demonstrated promising effectiveness in this area. Nonetheless, these LLMs often fail…
Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work addresses this challenge using Retrieval-Augmented Generation (RAG) frameworks…
Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding…
Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…
Text indexing is a classical algorithmic problem that has been studied for over four decades: given a text $T$, pre-process it off-line so that, later, we can quickly count and locate the occurrences of any string (the query pattern) in $T$…
This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-based document…
Programmers make rich use of natural language in the source code they write through identifiers and comments. Source code identifiers are selected from a pool of tokens which are strongly related to the meaning, naming conventions, and…
Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear,…
Despite the continuous efforts in improving both the effectiveness and efficiency of code search, two issues remained unsolved. First, programming languages have inherent strong structural linkages, and feature mining of code as text form…
Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks. Despite numerous efforts made to optimize LLMs for long contexts, challenges persist in robustly processing long inputs. In…
In this paper, we generalize the well-known index coding problem to exploit the structure in the source-data to improve system throughput. In many applications, the data to be transmitted may lie (or can be well approximated) in a…
Named Entity Recognition (NER) is a fundamental problem in natural language processing (NLP). However, the task of extracting longer entity spans (e.g., awards) from extended texts (e.g., homepages) is barely explored. Current NER methods…
Recent advances in machine learning have significantly improved the understanding of source code data and achieved good performance on a number of downstream tasks. Open source repositories like GitHub enable this process with rich…
Link prediction is a fundamental task in graph machine learning with widespread applications such as recommendation systems, drug discovery, knowledge graphs, etc. In the foundation model era, how to develop universal link prediction…
The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce…
Large Language Model (LLM)-based agents increasingly rely on APIs to operate complex web applications, but rapid evolution often leads to incomplete or inconsistent API documentation. Existing work falls into two categories: (1) static,…
The paper presents the Source Code Analysis and Lexical Annotation Runtime (SCALAR), a tool specialized for mapping (annotating) source code identifier names to their corresponding part-of-speech tag sequence (grammar pattern). SCALAR's…
Block-based programming languages like Scratch have become increasingly popular as introductory languages for novices. These languages are intended to be used with a "tinkering" approach which allows learners and teachers to quickly…