PH
Pinjia He
cs.SEcs.CLcs.AIcs.CVcs.CRcs.LGcs.MMcs.DBcs.DCcs.HC
On Valency
published · living versionsW_bqdcau7f·v1 · currentpublished
Priority-Aware Scheduler for Serverless Functions Provision and Load Balancing
with Cheryl Lee, Zishan Su, Zhouruixing Zhu, Tianyi Yang +2
1 version
Preprints & journals
72 papers in the corpus · 2015–2026VisualTrust: Video Reasoning under On-Screen Claim Framing2610.21159v1 · Huachao Zhu, Junjielong Xu, Sicheng Li et al.2026 · 0 citationsarXiv
AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses2610.18090v1 · Kaiyu Huang, Yiting Li, Angyang Gu et al.2026 · 0 citationsarXiv
SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?2610.16870v1 · Zhiqing Zhong, Mingyu Chen, Aoyang Fang et al.2026 · 0 citationsarXiv
Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development2610.13022v1 · Mingyu Chen, Zhiqing Zhong, Manyi Wang et al.2026 · 0 citationsarXiv
Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis2608.21310v2 · Qisheng Lu, Aoyang Fang, Junjielong Xu et al.2026 · 0 citationsarXiv
PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks2607.28587v2 · Manyi Wang, Junjielong Xu, Pinjia He2026 · 0 citationsarXiv
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment2607.16242v2 · Changyue Li, Jiaming He, Youliang Yuan et al.2026 · 0 citationsarXiv
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision2606.27154v2 · Aoyang Fang, Yifan Yang, Jin'ao Shang et al.2026 · 0 citationsarXiv
PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning2606.02443v1 · Yusong Zhao, Yuejin Xie, Youliang Yuan et al.2026 · 0 citationsarXiv
SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs2604.22134v1 · Sihang Zhao, Kangrui Yu, Youliang Yuan et al.2026 · 2 citationsarXiv
Gleaner: A Semantically-Rich and Efficient Online Sampler for Microservice Diagnostics2604.16810v1 · Yifan Yang, Aoyang FANG, Songhan Zhang et al.2026 · 0 citationsarXiv
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark2603.00520v1 · Boxi Yu, Yang Cao, Yuzhong Zhang et al.2026 · 0 citationsarXiv
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context2602.12108v1 · Xiaoyuan Liu, Tian Liang, Dongyang Ma et al.2026 · 0 citationsarXiv
DeLog: An Efficient Log Compression Framework with Pattern Signature Synthesis2601.15084v2 · Siyu Yu, Yifan Wu, Junjielong Xu et al.2026 · 1 citationarXiv
MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning2601.07005v1 · Jianbo Yu, Yixuan Li, Hai Xu et al.2026 · 0 citationsProceedings of the AAAI Conference on Artificial Intelligence 40(2) (2026) 1480-1488
BackportBench: A Multilingual Benchmark for Automated Backporting of Patches2512.01396v1 · Zhiqing Zhong, Jiaming Huang, Pinjia He2025 · 0 citationsarXiv
Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation2511.20002v3 · Changyue Li, Jiaying Li, Youliang Yuan et al.2025 · 0 citationsarXiv
DynaCausal: Dynamic Causality-Aware Root Cause Analysis for Distributed Microservices2510.22613v1 · Songhan Zhang, Aoyang Fang, Yifan Yang et al.2025 · 0 citationsarXiv
CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Series2510.22619v1 · Songhan Zhang, Yuanhao Lai, Pengfei Zheng et al.2025 · 0 citationsarXiv
Scalable Supervision for Software Agents via Patch Reasoning2510.22775v2 · Junjielong Xu, Boyin Tan, Xiaoyuan Liu et al.2025 · 1 citationarXiv
A Goal-Driven Survey on Root Cause Analysis2510.19593v1 · Aoyang Fang, Haowen Yang, Haoze Dong et al.2025 · 0 citationsarXiv
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards2510.07774v3 · Youliang Yuan, Qiuyang Mang, Jingbang Chen et al.2025 · 0 citationsarXiv
Rethinking the Evaluation of Microservice RCA with a Fault Propagation-Aware Benchmark2510.04711v2 · Aoyang Fang, Songhan Zhang, Yifan Yang et al.2025 · 1 citationarXiv
UniSage: A Unified and Post-Analysis-Aware Sampling for Microservices2509.26336v2 · Zhouruixing Zhu, Zhihan Jiang, Tianyi Yang et al.2025 · 0 citationsarXiv
Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach2509.13774v1 · Piaopiao Jin, Qi Wang, Guokang Sun et al.2025 · 0 citationsarXiv
SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints2509.09853v2 · Zhiyu Fan, Kirill Vasilevski, Dayi Lin et al.2025 · 0 citationsarXiv
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench2506.09289v1 · Boxi Yu, Yuxuan Zhu, Pinjia He et al.2025 · 4 citationsACL 2025
Towards Evaluating Proactive Risk Awareness of Multimodal Language Models2505.17455v2 · Youliang Yuan, Wenxiang Jiao, Yuejin Xie et al.2025 · 1 citationarXiv
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards2505.13445v1 · Xiaoyuan Liu, Tian Liang, Zhiwei He et al.2025 · 2 citationsarXiv
Let AI Read First: Enhancing Reading Abilities for Individuals with Dyslexia through Artificial Intelligence2504.00941v1 · Sihang Zhao, Shoucong Carol Xiong, Bo Pang et al.2025 · 15 citationsarXiv
Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs2502.16435v5 · Jen-Tse Huang, Dasen Dai, Jen-Yuan Huang et al.2025 · 2 citationsarXiv
Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs2502.11184v2 · Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao et al.2025 · 4 citationsarXiv
AL-Bench: A Benchmark for Automatic Logging2502.03160v3 · Boyin Tan, Junjielong Xu, Zhouruixing Zhu et al.2025 · 2 citationsarXiv
Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility2501.10711v5 · Jialun Cao, Yuk-Kit Chan, Zixuan Ling et al.2025 · 0 citationsarXiv
Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs2410.11437v1 · Sihang Zhao, Youliang Yuan, Xiaoying Tang et al.2024 · 1 citationarXiv
Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs2410.08145v2 · Xiaoyuan Liu, Wenxuan Wang, Youliang Yuan et al.2024 · 0 citationsarXiv
An Empirical Study on Package-Level Deprecation in Python Ecosystem2408.10327v1 · Zhiqing Zhong, Shilin He, Haoxuan Wang et al.2024 · 9 citationsarXiv
Unlocking the Power of Numbers: Log Compression via Numeric Token Parsing2408.05760v1 · Siyu Yu, Yifan Wu, Ying Li et al.2024 · 8 citationsarXiv
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training2407.09121v2 · Youliang Yuan, Wenxiang Jiao, Wenxuan Wang et al.2024 · 7 citationsarXiv
On the Influence of Data Resampling for Deep Learning-Based Log Anomaly Detection: Insights and Recommendations2405.03489v3 · Xiaoxue Ma, Huiqi Zou, Pinjia He et al.2024 · 15 citationsarXiv
Aligning the Objective of LLM-based Program Repair2404.08877v5 · Junjielong Xu, Ying Fu, Shin Hwei Tan et al.2024 · 15 citationsarXiv
SPES: Towards Optimizing Performance-Resource Trade-Off for Serverless Functions2403.17574v2 · Cheryl Lee, Zhouruixing Zhu, Tianyi Yang et al.2024 · 13 citationsarXiv
Go Static: Contextualized Logging Statement Generation2402.12958v1 · Yichen Li, Yintong Huo, Renyi Zhong et al.2024 · 24 citationsarXiv
LogPTR: Variable-Aware Log Parsing with Pointer Network2401.05986v2 · Yifan Wu, Bingxu Chai, Siyu Yu et al.2024 · 2 citationsarXiv
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models2401.00757v3 · Yuxuan Wan, Wenxuan Wang, Yiliu Yang et al.2024 · 16 citationsarXiv
Retromorphic Testing: A New Approach to the Test Oracle Problem2310.06433v1 · Boxi Yu, Qiuyang Mang, Qingshuo Guo et al.2023 · 0 citationsarXiv
LILAC: Log Parsing using LLMs with Adaptive Parsing Cache2310.01796v3 · Zhihan Jiang, Jinyang Liu, Zhuangbin Chen et al.2023 · 128 citationsarXiv
AutoLog: A Log Sequence Synthesis Framework for Anomaly Detection2308.09324v1 · Yintong Huo, Yichen Li, Yuxin Su et al.2023 · 16 citationsarXiv
An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software2308.09810v1 · Wenxuan Wang, Jingyuan Huang, Jen-tse Huang et al.2023 · 8 citationsarXiv
Hue: A User-Adaptive Parser for Hybrid Logs2308.07085v1 · Junjielong Xu, Qiuai Fu, Zhouruixing Zhu et al.2023 · 17 citationsarXiv
Career total: 134 works. 72 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.