Software Engineering

Silin Chen, Shaoxin Lin, Xiaodong Gu et al.

This addresses the inefficiency of redundant exploration in automated software engineering for developers, representing a new paradigm rather than an incremental improvement.

Anne Ouyang, Simon Guo, Simran Arora et al.

This work addresses the problem of efficient GPU kernel generation for machine learning architectures, which is significant for ML engineers and researchers.

Chenchen Zhang, Yuhang Li, Can Xu et al.

This addresses the problem of assessing visual and interactive quality in code generation for developers and researchers, representing a novel paradigm rather than an incremental improvement.

Anjiang Wei, Tianran Sun, Yogesh Seenichamy et al. · stanford

This addresses the challenge of manual tuning for GPU kernels in high-performance computing and machine learning, particularly for LLM training and serving, representing a novel paradigm rather than an incremental improvement.

Chenyuan Yang, Zijie Zhao, Zichen Xie et al.

This addresses the problem of scalable and reliable bug detection in critical systems like operating system kernels, representing a new paradigm rather than an incremental improvement.

Hao Wang, Zeyu Gao, Chao Zhang et al.

This work addresses transferability issues in binary analysis for security and software engineering, offering a novel approach with broad applicability.

Yifeng Ding, Jiawei Liu, Yuxiang Wei et al.

This addresses the challenge of enhancing code generation capabilities for developers and researchers, offering a novel approach that is fully orthogonal to existing techniques.

Kyle Thompson, Nuno Saavedra, Pedro Carrott et al.

This addresses the high expertise and manual effort required in formal software verification, offering a significant improvement in automation for developers and researchers.

Juyong Jiang, Jiasi Shen, Sunghun Kim et al.

This work significantly improves the code generation capabilities of large language models by internalizing self-reflection and self-correction, which is crucial for developers and researchers working on complex algorithmic tasks.

Yiheng Xiong, Ting Su, Jingling Sun et al.

This addresses the adoption barrier of property-based testing for mobile app developers by automating a labor-intensive task.

Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim et al.

This work addresses the challenge of time complexity prediction for developers working with limited resources, providing a significant improvement over existing self-training approaches.

Md Shafiuzzaman, Achintya Desai, Wenbo Guo et al.

This addresses the scalability limitation of symbolic execution for vulnerability detection in software security, representing a novel integration rather than an incremental improvement.

Rui Yang, Michael Fu, Chakkrit Tantithamthavorn et al.

This addresses a critical software engineering challenge for deploying safe LLMs by enabling guardrails to adapt dynamically to emerging threats post-deployment.

Zhengren Wang, Rui Ling, Chufan Wang et al.

It addresses the critical issue of maintainability in real-world software development for code generation systems, offering a novel benchmark and method.

Lei Ma, Jinyang Liu, Tieying Zhang et al.

This addresses the challenge of detecting system failures and security risks in logs for industries like cloud computing, offering a novel approach that improves accuracy and efficiency over prior methods.

Yihao Zhang, Zeming Wei, Xiaokun Luan et al.

This addresses critical security risks for users of interconnected multi-agent systems, exposing vulnerabilities that could lead to autonomous attacks without attacker intervention.

Zhiyuan Zeng, Yichi Zhang, Yong Shan et al.

This addresses the problem of LLMs' shallow reasoning in software engineering for developers and AI researchers, representing a new paradigm rather than incremental work.

Evan Hubinger, Carson Denison, Jesse Mu et al.

This study highlights a critical safety vulnerability in AI systems, showing that deceptive strategies can persist through current training methods, posing risks for applications relying on trustworthy models.

Chunqiu Steven Xia, Zhe Wang, Yan Yang et al.

This addresses the need for more adaptive and efficient software engineering agents for developers, though it builds on prior self-improving agent concepts.

Ahilan Ayyachamy Nadar Ponnusamy

This work addresses the problem of evaluating AI-generated code quality for software developers, particularly junior developers who may struggle to critically evaluate the generated code.