Get started
Author

Michael R. Lyu

Observed names: Lyu, Michael R., Michael R Lyu
Observed institution: Chinese University of Hong Kong
ORCID: 0000-0002-3666-5798
Observed ORCID: 0000-0002-3666-5798
OpenAlex ID: A5127959574
Towards Efficient Post-Training Quantization of Pre-Trained Language Models
2022 · Haoli Bai, Lu Hou, et al. · neural information processing systems · 35
PDF
SWE-MEM: Learning Adaptive Memory Management for Long-Horizon Coding Agents
2026 · Shuzheng Gao, Wenhao Zeng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 21
PDF
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems
2026 · Wang, Yilun, Yu, Guangba, et al. · arXiv (Cornell University) · 20
PDF
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
2026 · Lam, Man Ho, Wang, Chaozheng, et al. · arXiv (Cornell University) · 18
PDF
EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection
2026 · Tang, Wenxin, Xiao, Jingyu, et al. · arXiv (Cornell University) · 13
PDF
ComUICoder: Component-based Reusable UI Code Generation for Complex Websites via Semantic Segmentation and Element-wise Feedback
2026 · Xiao, Jingyu, Qin, Jiantong, et al. · arXiv (Cornell University) · 12
PDF
Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs
2026 · Yu, Guangba, Wang, Zirui, et al. · arXiv (Cornell University) · 6
PDF
From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level
2026 · Jia Li, Yuxin Su, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 6
PDF
VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair
2026 · Xiao, Jingyu, Zhang, Zhongyi, et al. · arXiv (Cornell University) · 4
PDF
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis
2026 · Huang, Haiyu, Lyu, Jiewei, et al. · arXiv (Cornell University) · 3
PDF
Hierarchical Prediction-based Management for LMaaS Systems
2025 · Jiang, Zhihan, Huang, Yujie, et al. · arXiv (Cornell University) · 3
PDF
Automated Logging Is Language-Sensitive: A Multilingual Benchmark and Empirical Study of LLMs
2026 · Renyi Zhong, Yichen Li, et al. · ACM Transactions on Software Engineering and Methodology · 1
PDF
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
2026 · Fan, Tsz Hei, Fung, Choi Wing, et al. · arXiv (Cornell University) · 1
PDF
VideoLatent: Video-Language Learning via Latent Self-Forcing
2026 · Hu, Zi-Yuan, Tang, Zicong, et al. · arXiv (Cornell University) · 1
PDF
ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair
2026 · Li, Jia, Zhuang, Zeyang, et al. · arXiv (Cornell University) · 1
PDF
Artifact for paper "MicroAgent: Context-Augmented Multi-agent Framework for Automatic Microservice Decomposition" (ASE'26)
2026 · Su, Zishan, Huang, Junjie, et al. · Zenodo (CERN European Organization for Nuclear Research) · 1
TraceLite: Efficient Trace Reduction for SWE Agents via Optical Compression and Redundancy Removal
2026 · Xiao, Jingyu, Liu, Qianxi, et al. · arXiv (Cornell University)
PDF
MicroAgent: Context-Augmented Multi-agent Framework for Automatic Microservice Decomposition
2026 · Zishan Su, Junjie Huang, et al. · IEEE/ACM International Conference on Automated Software Engineering (ASE)
MatLoom: Layered Text-to-Material Generation in a Compact Program Space
2026 · Lam, Anson Y., Li, Shuqing, et al. · arXiv (Cornell University)
PDF
Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation
2026 · Lam, Anson Y., Li, Shuqing, et al. · arXiv (Cornell University)
PDF
Artifact for "StaR: Stateful Dynamic-Graph Root Cause Analysis through Memory-Enhanced Causality Discovery"
2026 · Huang, Haiyu, Ng, Derek, et al. · Zenodo (CERN European Organization for Nuclear Research)
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
2026 · Li, Jia, Su, Yuxin, et al. · arXiv (Cornell University)
PDF
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective
2026 · Chen, Meifang, Yang, Zhe, et al. · arXiv (Cornell University)
PDF
Works count: 26
Citation count: 146
H-index: 6
I10-index: 6
Year
Topic
Type