5 papers
Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization
Minghao Li, Rui Tan, Ruihang Wang
Designing dense reward functions for low-level reinforcement learning (RL) control remains difficult. Recent work uses large language models (LLMs) to iteratively generate and refi…
DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations
Minghao Li, Ruihang Wang, Rui Tan +1
Modern data centers (DCs) hosting artificial intelligence (AI)-dedicated devices operate at high power densities with rapidly varying workloads, making minute-level adaptation esse…
Phythesis: Physics-Guided Evolutionary Scene Synthesis for Energy-Efficient Data Center Design via LLMs
Minghao LI, Ruihang Wang, Rui Tan +1
Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with spe…
Fusion Intelligence for Digital Twinning AI Data Centers: A Synergistic GenAI-PhyAI Approach
Ruihang Wang, Minghao Li, Zhiwei Cao +3
The explosion in artificial intelligence (AI) applications is pushing the development of AI-dedicated data centers (AIDCs), creating management challenges that traditional methods…
Transforming Future Data Center Operations and Management via Physical AI
Zhiwei Cao, Minghao Li, Feng Lin +4
Data centers (DCs) as mission-critical infrastructures are pivotal in powering the growth of artificial intelligence (AI) and the digital economy. The evolution from Internet DC to…