SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference (Preprint, 2025): An SLO-oriented LLM serving system that maximizes goodput and SLO attainment via adaptive scheduling
Exploring Multimodal Prompt for Visualization Authoring with Large Language Models (Preprint, 2025): A novel approach to visualization authoring using multimodal prompts with LLMs
DataLab: A Unified Platform for LLM-Powered Business Intelligence (ICDE 2025): A unified BI platform integrating an LLM-based agent framework with an augmented computational notebook
DLRover-RM: Resource Optimization for Deep Recommendation Models Training in the Cloud (VLDB 2024): Efficient resource management system for training deep recommendation models in the cloud
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts (Preprint, 2024): A LoRA-based MoE approach to improve LLM fine-tuning efficiency and performance