6 papers
Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
Kunjal Panchal, Saayan Mitra, Sunav Choudhary +3
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two co…
Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis
Zhenning Yang, Kaden Gruizenga, Tongyuan Miao +3
The scale and complexity of modern cloud infrastructure have made Infrastructure-as-Code (IaC) essential for managing deployments. While large Language models (LLMs) are increasing…
HADIS: Hybrid Adaptive Diffusion Model Serving for Efficient Text-to-Image Generation
Qizheng Yang, Tung-I Chen, Siyu Zhao +2
Text-to-image diffusion models have achieved remarkable visual quality but incur high computational costs, making latency-aware, scalable deployment challenging. To address this, w…
Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse
Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel +4
Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficientl…
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…
DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
Sohaib Ahmad, Qizheng Yang, Haoliang Wang +2
Text-to-image generation using diffusion models has gained increasing popularity due to their ability to produce high-quality, realistic images based on text prompts. However, effi…