2024

Deepot: Parking Lot Identification Using Low-Resolution Satellite Imagery
Deepot: Parking Lot Identification Using Low-Resolution Satellite Imagery

Xianzhong Ding, Wanshi Hong, Zhiyu An, Bin Wang, Wan Du

The 58th Hawaii International Conference on System Sciences (HICSS) 2025 Best Paper Award

Deepot: Parking Lot Identification Using Low-Resolution Satellite Imagery

Xianzhong Ding, Wanshi Hong, Zhiyu An, Bin Wang, Wan Du

The 58th Hawaii International Conference on System Sciences (HICSS) 2025 Best Paper Award

Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base
Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base

Zhiyu An, Xianzhong Ding, Yen-Chun Fu, Cheng-Chung Chu, Yan Li, Wan Du

arXiv 2024

We proposed a Large Language Model (LLM) thought process for Retrieval-Augmented Generation (RAG) that avoids misinterpreting jargons and abbreviations when it is not sure what they mean.

Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base

Zhiyu An, Xianzhong Ding, Yen-Chun Fu, Cheng-Chung Chu, Yan Li, Wan Du

arXiv 2024

We proposed a Large Language Model (LLM) thought process for Retrieval-Augmented Generation (RAG) that avoids misinterpreting jargons and abbreviations when it is not sure what they mean.

MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge
MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge

Yuning Chen, Kang Yang, Zhiyu An, Brady Holder, Luke Paloutzian, Khaled M. Bali, Wan Du

The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2024

MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge

Yuning Chen, Kang Yang, Zhiyu An, Brady Holder, Luke Paloutzian, Khaled M. Bali, Wan Du

The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2024

Reward Bound for Behavioral Guarantee of Model-Based Planning Agents
Reward Bound for Behavioral Guarantee of Model-Based Planning Agents

Zhiyu An, Xianzhong Ding, Wan Du

Tiny Paper Track, International Conference on Learning Representations (ICLR) 2024

Reward Bound for Behavioral Guarantee of Model-Based Planning Agents

Zhiyu An, Xianzhong Ding, Wan Du

Tiny Paper Track, International Conference on Learning Representations (ICLR) 2024

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control

Zhiyu An, Xianzhong Ding, Wan Du

The 61st ACM/IEEE Design Automation Conference (DAC) 2024

We found an efficient way to distill a learned HVAC-controlling policy to a decision tree, thereby enabling engineers to easily verify the safety of policy's decisions and load the policy onto an edge device.

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control

Zhiyu An, Xianzhong Ding, Wan Du

The 61st ACM/IEEE Design Automation Conference (DAC) 2024

We found an efficient way to distill a learned HVAC-controlling policy to a decision tree, thereby enabling engineers to easily verify the safety of policy's decisions and load the policy onto an edge device.

2023

CLUE: Safe Model-Based RL HVAC Control Using Epistemic Uncertainty Estimation
CLUE: Safe Model-Based RL HVAC Control Using Epistemic Uncertainty Estimation

Zhiyu An, Xianzhong Ding, Arya Rathee, Wan Du

ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) 2023 Best Paper Runner-Up

We designed an energy-saving HVAC scheduling algorithm that improves its decisions using data, and can make conservative decisions when it lacks knowledge about an unfamiliar situation.

CLUE: Safe Model-Based RL HVAC Control Using Epistemic Uncertainty Estimation

Zhiyu An, Xianzhong Ding, Arya Rathee, Wan Du

ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) 2023 Best Paper Runner-Up

We designed an energy-saving HVAC scheduling algorithm that improves its decisions using data, and can make conservative decisions when it lacks knowledge about an unfamiliar situation.

Data Efficient HVAC Control using Gaussian Process-based Reinforcement Learning
Data Efficient HVAC Control using Gaussian Process-based Reinforcement Learning

Zhiyu An, Xianzhong Ding, Wan Du

The ACM Conference on Embedded Networked Sensor Systems (SenSys) 2023

Data Efficient HVAC Control using Gaussian Process-based Reinforcement Learning

Zhiyu An, Xianzhong Ding, Wan Du

The ACM Conference on Embedded Networked Sensor Systems (SenSys) 2023