Yingwei Ma

Orcid: 0000-0001-7630-4113

According to our database1, Yingwei Ma authored at least 34 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation.
CoRR, April, 2026

Scaling Coding Agents via Atomic Skills.
CoRR, April, 2026

DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder.
CoRR, February, 2026

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Large Language Model Unlearning for Source Code.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Multi-Docker-Eval: A 'Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering.
CoRR, December, 2025

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents.
CoRR, September, 2025

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization.
CoRR, August, 2025

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format.
CoRR, June, 2025

Large Language Model Unlearning for Source Code.
CoRR, June, 2025

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning.
CoRR, June, 2025

Efficient Reasoning via Chain of Unconscious Thought.
CoRR, May, 2025

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute.
CoRR, March, 2025

SWE-GPT: A Process-Centric Language Model for Automated Software Improvement.
Proc. ACM Softw. Eng., 2025

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration.
Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, 2025

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute.
Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering, 2025

FlipAttack: Jailbreak LLMs via Flipping.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

UTMath: A Benchmark for Math Evaluation with Unit Test.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Safety in Large Reasoning Models: A Survey.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024
LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues.
CoRR, 2024

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement.
CoRR, 2024

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks.
CoRR, 2024

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
CoRR, 2024

How to Understand Whole Software Repository?
CoRR, 2024

Online Differentiable Clustering for Intent Learning in Recommendation.
CoRR, 2024

End-to-end Learnable Clustering for Intent Learning in Recommendation.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

At Which Training Stage Does Code Data Help LLMs Reasoning?
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Language-Enhanced Session-Based Recommendation with Decoupled Contrastive Learning.
CoRR, 2023

MulCS: Towards a Unified Deep Representation for Multilingual Code Search.
Proceedings of the IEEE International Conference on Software Analysis, 2023

Automatic Code Annotation Generation Based on Heterogeneous Graph Structure.
Proceedings of the IEEE International Conference on Software Analysis, 2023

A Two-Stage Framework for Ambiguous Classification in Software Engineering.
Proceedings of the 34th IEEE International Symposium on Software Reliability Engineering, 2023

Towards Better Multilingual Code Search through Cross-Lingual Contrastive Learning.
Proceedings of the 14th Asia-Pacific Symposium on Internetware, 2023

2022
Accelerating OCR-Based Widget Localization for Test Automation of GUI Applications.
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, 2022


  Loading...