36 citations · 42 across the 14 of their papers we have counts for
14 papers
Automated Synthesis of Cloud Emulators
Archit Bhatnagar, Zhenning Yang, Sarah McClure +3
DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure management. Unlike traditional programming tasks, DevOps program testing needs pro…
scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology
Ian Diks, Zhen Yang, Arjun Banerjee +2
Single-cell studies require analysts to convert raw measurements into specific biological claims through multi-step workflows and integration of metadata, assay context, and auxili…
SPARC: A Multi-Agent System for Electrical Circuit Question Answering
Mushtari Sadia, Zhenning Yang, Umme Habiba Lamia +3
Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers quest…
Interactive Clarification for Cloud Infrastructure-as-Code Synthesis
Zhenning Yang, Kaden Gruizenga, Tongyuan Miao +4
The scale and complexity of modern cloud infrastructure have made "Infrastructure-as-Code" (IaC) essential for managing deployments through declarative configurations. While large…
Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents
Zhenning Yang, Hui Guan, Victor Nicolet +4
Cloud infrastructure is managed through a mix of interfaces -- traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastruct…
Cloud Infrastructure Management in the Age of AI Agents
Zhenning Yang, Archit Bhatnagar, Yiming Qiu +6
Cloud infrastructure is the cornerstone of the modern IT industry. However, managing this infrastructure effectively requires considerable manual effort from the DevOps engineering…
SQUiD: Synthesizing Relational Databases from Unstructured Text
Mushtari Sadia, Zhenning Yang, Yunming Xiao +2
Relational databases are central to modern data management, yet most data exists in unstructured forms like text documents. To bridge this gap, we leverage large language models (L…
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding +7
Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing…
Disaggregating Embedding Recommendation Systems with FlexEMR
Yibo Huang, Zhenning Yang, Jiarong Xing +5
Efficiently serving embedding-based recommendation (EMR) models remains a significant challenge due to their increasingly large memory requirements. Today's practice splits the mod…
Adversarial Attacks and Defense for Conversation Entailment Task
Zhenning Yang, Ryan Krawec, Liang-Yuan Wu
As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important.…
Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Insu Jang, Zhenning Yang, Zhen Zhang +2
Oobleck enables resilient distributed training of large DNN models with guaranteed fault tolerance. It takes a planning-execution co-design approach, where it first generates a set…
Chasing Low-Carbon Electricity for Practical and Sustainable DNN Training
Zhenning Yang, Luoxi Meng, Jae-Won Chung +1
Deep learning has experienced significant growth in recent years, resulting in increased energy consumption and carbon emission from the use of GPUs for training deep neural networ…
SLRNet: Semi-Supervised Semantic Segmentation Via Label Reuse for Human Decomposition Images
Sara Mousavi, Zhenning Yang, Kelley Cross +2
Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process…
Pseudo Pixel-level Labeling for Images with Evolving Content
Sara Mousavi, Zhenning Yang, Kelley Cross +2
Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Fore…