Aaron R. Sun

Evaluating Agent-Based Program Repair at Google

Pat Rondon, José Cambronero, Jürgen Cito, Aaron R. Sun et autres

Agent-based program repair offers to automatically resolve complex bugs end-to-end by combining the planning, tool use, and code generation abilities of modern LLMs. Recent work has explored the use of agent-based repair approaches on the popular open-source SWE-Bench [1], a collection of …

us (code pays fourni par la source)

Agentic Bug Reproduction for Effective Automated Program Repair at Google

Michele Tufano, Jürgen Cito, José Cambronero, Pat Rondon et autres

Bug reports often lack sufficient detail for developers to reproduce and fix the underlying defects. Bug Reproduction Tests (BRTs), tests that fail when the bug is present and pass when it has been resolved, are crucial for debugging, but they are rarely …

Merlin L48 Spectrogram Dataset

Aaron R. Sun, Subhransu Maji, Grant Van Horn

In the single-positive multi-label (SPML) setting, each image in a dataset is labeled with the presence of a single class, while the true presence of other classes remains unknown. The challenge is to narrow the performance gap between this partially-labeled setting and …

us (code pays fourni par la source)

A Systematic Framework for Sentiment Identification by Modeling User Social Effects

Kunpeng Zhang, Yi Yang, Aaron R. Sun, Hengchang Liu

Social media is becoming a major and popular technological platform that allows users to express personal opinions toward the subjects with shared interests. Identifying the sentiments of these social media data can help users make informed decisions. Existing research mainly focus on …

us, cn (code pays fourni par la source)

Incorporating conditional random fields and active learning to improve sentiment identification

Kunpeng Zhang, Yusheng Xie, Yi Yang, Aaron R. Sun et autres

us, ph, kr, cn (code pays fourni par la source)

An Information Diffusion-Based Recommendation Framework for Micro-Blogging

Jiesi Cheng, Aaron R. Sun, Daning Hu, Daniel Dajun Zeng

Micro-blogging is increasingly evolving from a daily chatting tool into a critical platform for individuals and organizations to seek and share real-time news updates during emergencies. However, seeking and extracting useful information from micro-blogging sites poses significant challenges due to the volume …

us, ch (code pays fourni par la source)

Burst Detection From Multiple Data Streams: A Network-Based Approach

Aaron R. Sun, Daniel Dajun Zeng, Hsinchun Chen

Modeling and detecting bursts in data streams is an important area of research with a wide range of applications. In this paper, we present a novel method to analyze and identify correlated burst patterns by considering multiple data streams that coevolve over …

us (code pays fourni par la source)

Maximizing Influence Through Information-Overloaded Online Social Networks

Aaron R. Sun, Jiesi Cheng, Daniel Dajun Zeng

us (code pays fourni par la source)

An Information Diffusion Based Recommendation Framework for Micro-Blogging

Jiesi Cheng, Aaron R. Sun, Daning Hu, Daniel Dajun Zeng

us, hk, ch (code pays fourni par la source)

Information Overload and Viral Marketing: Countermeasures and Strategies

Jiesi Cheng, Aaron R. Sun, Daniel Dajun Zeng

us, cn (code pays fourni par la source)

A Novel Recommendation Framework for Micro-Blogging Based on Information Diffusion

Aaron R. Sun, Jiesi Cheng, Daniel Dajun Zeng

Abstract. Micro-blogging is increasingly extending its role from a daily chatting tool into a critical platform for individuals and organizations to seek and share real-time news updates during emergencies. However, extracting useful information from micro-blogging sites poses significant challenges due to the …

us (code pays fourni par la source)

Network-Based Analysis of Beijing SARS Data

Xiaolong Zheng, Daniel Dajun Zeng, Aaron R. Sun, Yuan Luo et autres

cn, us (code pays fourni par la source)