Minlan Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Minlan Yu has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
- Michael Mitzenmacher
Harvard University, Cambridge, MA, USA
5 shared publications - Ran Ben Basat
University College London, London, United Kingdom
5 shared publications - Gianni Antichi
Politecnico di Milano & Queen Mary University of London, London, United Kingdom
3 shared publications - Alexander M. Rush
Cornell Tech, New York City, USA
2 shared publications - ChonLam Lao
Harvard University, Cambridge, MA, USA
2 shared publications - Haiying Shen
Department of Computer science, University of Virginia, Charlottesville, Virginia, USA
2 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 754-770
HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 754-770
Open AccessHACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
- Open Access
- 29 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 48-55
From Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
- 29 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 48-55
Open AccessFrom Barrier to Bridge: The Case for AI Data Center/Power Grid Co-Design
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 898-915
A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with CrystalLLM
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 898-915
Open AccessA Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with CrystalLLM
- Open Access
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 505-518
Connecting 100K+ GPUs: Building the Communication Stack for Large-Scale LLM Training
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 505-518
Open AccessConnecting 100K+ GPUs: Building the Communication Stack for Large-Scale LLM Training
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1322-1326
Orla: A Library for Serving LLM-Based Multi-Agent Systems
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1322-1326
Open AccessOrla: A Library for Serving LLM-Based Multi-Agent Systems
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Energy Sustainability Magazine
- Vol. 2  (1) , 22-28
Crucial Role of Foundation Models in Enhancing the Interaction of AI and Power Systems: Achieving Integrated Frameworks
The rapid emergence of large-scale generative artificial intelligence (GenAI) systems, or foundation models (FMs), presents a dual challenge and opportunity for global energy systems. While driving unprecedented computational demand and a sharp increase in electricity consumption for both training and inference, FMs also introduce significant volatility and unpredictability into power loads. This necessitates a fundamental re-evaluation of short-term grid operations and long-term infrastructure planning. This article argues that the same advanced AI capabilities responsible for this energy disruption can also be leveraged to develop smarter and more resilient energy management solutions. We propose an integrated framework where FMs serve as tools for optimizing data center energy efficiency and enhancing grid control, advocating for a converging research frontier that integrates AI, power systems, and market design to navigate the energy implications of advanced AI sustainably.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Energy Sustainability Magazine
- Vol. 2  (1) , 22-28
Crucial Role of Foundation Models in Enhancing the Interaction of AI and Power Systems: Achieving Integrated Frameworks
The rapid emergence of large-scale generative artificial intelligence (GenAI) systems, or foundation models (FMs), presents a dual challenge and opportunity for global energy systems. While driving unprecedented computational demand and a sharp increase in electricity consumption for both training and inference, FMs also introduce significant volatility and unpredictability into power loads. This necessitates a fundamental re-evaluation of short-term grid operations and long-term infrastructure planning. This article argues that the same advanced AI capabilities responsible for this energy disruption can also be leveraged to develop smarter and more resilient energy management solutions. We propose an integrated framework where FMs serve as tools for optimizing data center energy efficiency and enhancing grid control, advocating for a converging research frontier that integrates AI, power systems, and market design to navigate the energy implications of advanced AI sustainably.
- Open Access
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 280-288
Your network doesn't end at the NIC
- 17 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 280-288
Open AccessYour network doesn't end at the NIC
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 254-269
Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 254-269
Open AccessMycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training
- Open Access
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1245-1247
HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1245-1247
Open AccessHACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
- Top Cited PapersOpen Access
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 347-362
Intent-Driven Network Management with Multi-Agent LLMs: The Confucius Framework
- 27 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 347-362
Top Cited PapersOpen AccessIntent-Driven Network Management with Multi-Agent LLMs: The Confucius Framework