Related papers: CodeR3: A GenAI-Powered Workflow Repair and Reviva…

Generative AI (GenAI) systems offer unprecedented opportunities for transforming professional and personal work, yet present challenges around prompting, evaluating and relying on outputs, and optimizing workflows. We argue that…

Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes often shift (temporal drift), reducing the credibility of the analysis. Existing…

Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures. Coded-InvNet leverages…

Erasure coding is a storage-efficient alternative to replication for achieving reliable data backup in distributed storage systems. During the storage process, traditional erasure codes require a unique source node to create and upload all…

When done manually, refactoring legacy code in order to eliminate uses of deprecated APIs is an error-prone and time-consuming process. In this paper, we investigate to which degree refactorings for deprecated Java APIs can be automated,…

Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow…

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

As Generative AI (GenAI) capabilities expand, understanding how to preserve and develop human expertise while leveraging AI's benefits becomes increasingly critical. Through empirical studies in two contexts -- survey article authoring in…

This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is…

The 3rd Generation Partnership Project (3GPP) produces complex technical specifications essential to global telecommunications, yet their hierarchical structure, dense formatting, and multi-modal content make them difficult to process.…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a…

Traditional high-quality 3D scanning and reconstruction typically relies on human labor to plan the scanning procedure. With the rapid development of embodied systems such as drones and robots, there is a growing demand of performing…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to enhance large language models (LLMs) by integrating external knowledge retrieval with generative capabilities. While significant advancements have been…

Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…

Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conversations, legal documents, or retrieved documents in…

In a new effort to make our research transparent and reproducible by others, we developed a workflow to run and share computational studies on the public cloud Microsoft Azure. It uses Docker containers to create an image of the application…

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the…

Code summarization and code search have been widely adopted in sofwaredevelopmentandmaintenance. However, fewstudieshave explored the efcacy of unifying them. In this paper, we propose TranS^3 , a transformer-based framework to integrate…