Haoran Qiu

Senior Research Engineer

论文与出版物

查看方式：

- Benchmarking Long-Horizon Agent Context Compaction with CompactionBench
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Jingran Zhou, Rodrigo Fonseca, Ricardo Bianchini, Fan Lai, Esha Choukse
  
  October 2026
  
  October 2026
  
  Preprint
- PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response
  
  Yueying Li, Jiayang Chen, Yuanfan Chen, Leo Han, Haoran Qiu, Esha Choukse, Rodrigo Fonseca, Udit Gupta
  
  ArXiv | August 2026
  
  Preprint 项目
- OpScale: Operator-level Provisioning and Autoscaling for LLM Serving
  
  Xingqi Cui, Chieh-Jan Mike Liang, Ziang Tang, Jiarong Xing, Haoran Qiu
  
  ArXiv | August 2026
  
  Preprint 项目
- Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Esha Choukse
  
  arXiv | July 2026
  
  Preprint Document 项目
- Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  
  Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Adam Belay, Ricardo Bianchini
  
  OSDI 2026 | July 2026
  
  Preprint Publication 项目
- Beyond Prediction: Tail-Aware Scheduling for LLM Inference
  
  Yueying Li, Yuanfan Chen, Jiayang Chen, Esha Choukse, Haoran Qiu, Edward Suh, Rodrigo Fonseca, Zib Scully, Udit Gupta
  
  ICML 2026 | June 2026
  
  Publication Preprint 项目
- Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems
  
  Haoran Qiu, Phuong Cao, Shengkun Cui, Archit Patke, Ravishankar Iyer
  
  DSN 2026 | June 2026
  
  PDF
- No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  SoCC 2026 | April 2026
  
  Preprint
- StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
  
  Haoran Qiu, Gohar Irfan Chaudhry, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini
  
  March 2026
  
  Preprint 项目
- ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  ACM Symposium on Cloud Computing (SoCC) 2025 | November 2025
  
  Preprint 项目项目
- From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models
  
  Xingqi Cui, Chieh-Jan Mike Liang, Jiarong Xing, Haoran Qiu
  
  ArXiv | November 2025
  
  Preprint 项目
- Sherlock: Reliable and efficient workflow execution
  
  Yeonju Ro, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Aditya Akella, Zhangyang Wang, Mattan Erez, Esha Choukse
  
  November 2025
  
  Publication 项目
- Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  September 2025
  
  Arxiv | September 2025
  
  Publication 项目
- The Next Horizon of System Intelligence
  
  Chieh-Jan Mike Liang, Haoran Qiu, Francis Y. Yan, Tianyin Xu, Lidong Zhou
  
  September 2025
  
  SIGOPS Blog Series | September 2025
  
  Publication
- TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms
  
  Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Haoran Qiu, Rodrigo Fonseca, Josep Torrellas, Ricardo Bianchini
  
  ASPLOS | April 2025
  
  Preprint PDF DOI 项目
- ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  February 2025
  
  Arxiv | February 2025
  
  Publication 项目项目
- SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud
  
  Jovan Stojkovic, Pulkit Misra, Íñigo Goiri, Sam Whitlock, Esha Choukse, Mayukh Das, Chetan Bansal, Jason Lee, Zoey Sun, Haoran Qiu, Reed Zimmermann, Savyasachi Samal, Brijesh Warrier, Ashish Raniwala, Ricardo Bianchini
  
  ISCA | June 2024
  
  Publication

- Benchmarking Long-Horizon Agent Context Compaction with CompactionBench
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Jingran Zhou, Rodrigo Fonseca, Ricardo Bianchini, Fan Lai, Esha Choukse
  
  October 2026
  
  October 2026
  
  Preprint
- PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response
  
  Yueying Li, Jiayang Chen, Yuanfan Chen, Leo Han, Haoran Qiu, Esha Choukse, Rodrigo Fonseca, Udit Gupta
  
  ArXiv | August 2026
  
  Preprint 项目
- OpScale: Operator-level Provisioning and Autoscaling for LLM Serving
  
  Xingqi Cui, Chieh-Jan Mike Liang, Ziang Tang, Jiarong Xing, Haoran Qiu
  
  ArXiv | August 2026
  
  Preprint 项目
- Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Esha Choukse
  
  arXiv | July 2026
  
  Preprint Document 项目
- Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  
  Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Adam Belay, Ricardo Bianchini
  
  OSDI 2026 | July 2026
  
  Preprint Publication 项目
- Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems
  
  Haoran Qiu, Phuong Cao, Shengkun Cui, Archit Patke, Ravishankar Iyer
  
  DSN 2026 | June 2026
  
  PDF
- StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
  
  Haoran Qiu, Gohar Irfan Chaudhry, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini
  
  March 2026
  
  Preprint 项目
- ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  ACM Symposium on Cloud Computing (SoCC) 2025 | November 2025
  
  Preprint 项目项目
- From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models
  
  Xingqi Cui, Chieh-Jan Mike Liang, Jiarong Xing, Haoran Qiu
  
  ArXiv | November 2025
  
  Preprint 项目
- Sherlock: Reliable and efficient workflow execution
  
  Yeonju Ro, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Aditya Akella, Zhangyang Wang, Mattan Erez, Esha Choukse
  
  November 2025
  
  Publication 项目
- Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  September 2025
  
  Arxiv | September 2025
  
  Publication 项目
- ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  February 2025
  
  Arxiv | February 2025
  
  Publication 项目项目
- PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response
  
  Yueying Li, Jiayang Chen, Yuanfan Chen, Leo Han, Haoran Qiu, Esha Choukse, Rodrigo Fonseca, Udit Gupta
  
  ArXiv | August 2026
  
  Preprint 项目
- OpScale: Operator-level Provisioning and Autoscaling for LLM Serving
  
  Xingqi Cui, Chieh-Jan Mike Liang, Ziang Tang, Jiarong Xing, Haoran Qiu
  
  ArXiv | August 2026
  
  Preprint 项目
- Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  
  Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Adam Belay, Ricardo Bianchini
  
  OSDI 2026 | July 2026
  
  Preprint Publication 项目
- Beyond Prediction: Tail-Aware Scheduling for LLM Inference
  
  Yueying Li, Yuanfan Chen, Jiayang Chen, Esha Choukse, Haoran Qiu, Edward Suh, Rodrigo Fonseca, Zib Scully, Udit Gupta
  
  ICML 2026 | June 2026
  
  Publication Preprint 项目
- No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  SoCC 2026 | April 2026
  
  Preprint
- StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
  
  Haoran Qiu, Gohar Irfan Chaudhry, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini
  
  March 2026
  
  Preprint 项目
- ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  ACM Symposium on Cloud Computing (SoCC) 2025 | November 2025
  
  Preprint 项目项目
- From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models
  
  Xingqi Cui, Chieh-Jan Mike Liang, Jiarong Xing, Haoran Qiu
  
  ArXiv | November 2025
  
  Preprint 项目
- Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  September 2025
  
  Arxiv | September 2025
  
  Publication 项目
- The Next Horizon of System Intelligence
  
  Chieh-Jan Mike Liang, Haoran Qiu, Francis Y. Yan, Tianyin Xu, Lidong Zhou
  
  September 2025
  
  SIGOPS Blog Series | September 2025
  
  Publication
- TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms
  
  Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Haoran Qiu, Rodrigo Fonseca, Josep Torrellas, Ricardo Bianchini
  
  ASPLOS | April 2025
  
  Preprint PDF DOI 项目
- SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud
  
  Jovan Stojkovic, Pulkit Misra, Íñigo Goiri, Sam Whitlock, Esha Choukse, Mayukh Das, Chetan Bansal, Jason Lee, Zoey Sun, Haoran Qiu, Reed Zimmermann, Savyasachi Samal, Brijesh Warrier, Ashish Raniwala, Ricardo Bianchini
  
  ISCA | June 2024
  
  Publication

- Benchmarking Long-Horizon Agent Context Compaction with CompactionBench
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Jingran Zhou, Rodrigo Fonseca, Ricardo Bianchini, Fan Lai, Esha Choukse
  
  October 2026
  
  October 2026
  
  Preprint
- Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  September 2025
  
  Arxiv | September 2025
  
  Publication 项目
- The Next Horizon of System Intelligence
  
  Chieh-Jan Mike Liang, Haoran Qiu, Francis Y. Yan, Tianyin Xu, Lidong Zhou
  
  September 2025
  
  SIGOPS Blog Series | September 2025
  
  Publication
- ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  February 2025
  
  Arxiv | February 2025
  
  Publication 项目项目
- PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response
  
  Yueying Li, Jiayang Chen, Yuanfan Chen, Leo Han, Haoran Qiu, Esha Choukse, Rodrigo Fonseca, Udit Gupta
  
  ArXiv | August 2026
  
  Preprint 项目
- OpScale: Operator-level Provisioning and Autoscaling for LLM Serving
  
  Xingqi Cui, Chieh-Jan Mike Liang, Ziang Tang, Jiarong Xing, Haoran Qiu
  
  ArXiv | August 2026
  
  Preprint 项目
- Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale
  
  Banruo Liu, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Esha Choukse
  
  arXiv | July 2026
  
  Preprint Document 项目
- From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models
  
  Xingqi Cui, Chieh-Jan Mike Liang, Jiarong Xing, Haoran Qiu
  
  ArXiv | November 2025
  
  Preprint 项目
- Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  
  Gohar Irfan Chaudhry, Esha Choukse, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Adam Belay, Ricardo Bianchini
  
  OSDI 2026 | July 2026
  
  Preprint Publication 项目
- Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems
  
  Haoran Qiu, Phuong Cao, Shengkun Cui, Archit Patke, Ravishankar Iyer
  
  DSN 2026 | June 2026
  
  PDF
- Beyond Prediction: Tail-Aware Scheduling for LLM Inference
  
  Yueying Li, Yuanfan Chen, Jiayang Chen, Esha Choukse, Haoran Qiu, Edward Suh, Rodrigo Fonseca, Zib Scully, Udit Gupta
  
  ICML 2026 | June 2026
  
  Publication Preprint 项目
- No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha
  
  Amey Agrawal, Haoran Qiu, Junda Chen, Íñigo Goiri, Chaojie Zhang, Rayyan Shahid, Ramachandran Ramjee, Alexey Tumanov, Esha Choukse
  
  SoCC 2026 | April 2026
  
  Preprint
- ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving
  
  Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, Íñigo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca
  
  ACM Symposium on Cloud Computing (SoCC) 2025 | November 2025
  
  Preprint 项目项目
- TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms
  
  Jovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Haoran Qiu, Rodrigo Fonseca, Josep Torrellas, Ricardo Bianchini
  
  ASPLOS | April 2025
  
  Preprint PDF DOI 项目
- SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud
  
  Jovan Stojkovic, Pulkit Misra, Íñigo Goiri, Sam Whitlock, Esha Choukse, Mayukh Das, Chetan Bansal, Jason Lee, Zoey Sun, Haoran Qiu, Reed Zimmermann, Savyasachi Samal, Brijesh Warrier, Ashish Raniwala, Ricardo Bianchini
  
  ISCA | June 2024
  
  Publication
- StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
  
  Haoran Qiu, Gohar Irfan Chaudhry, Chaojie Zhang, Íñigo Goiri, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini
  
  March 2026
  
  Preprint 项目
- Sherlock: Reliable and efficient workflow execution
  
  Yeonju Ro, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Aditya Akella, Zhangyang Wang, Mattan Erez, Esha Choukse
  
  November 2025
  
  Publication 项目

Haoran Qiu

论文与出版物

Benchmarking Long-Horizon Agent Context Compaction with CompactionBench

PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems

No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha

StreamWise: Serving Multi-Modal Generation in Real-Time at Scale

ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving

From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models

Sherlock: Reliable and efficient workflow execution

Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation

The Next Horizon of System Intelligence

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving

SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud

Benchmarking Long-Horizon Agent Context Compaction with CompactionBench

PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems

StreamWise: Serving Multi-Modal Generation in Real-Time at Scale

ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving

From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models

Sherlock: Reliable and efficient workflow execution

Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation

ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving

PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha

StreamWise: Serving Multi-Modal Generation in Real-Time at Scale

ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving

From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models

Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation

The Next Horizon of System Intelligence

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud

Benchmarking Long-Horizon Agent Context Compaction with CompactionBench

Medha: Efficient LLM Inference on Multi-Million Context Lengths Without Approximation

The Next Horizon of System Intelligence

ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving

PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving

Agentic Coding in the Wild: Characterizing GitHub Copilot at Production Scale

From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models

Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms

Fast or Slow? Human-Inspired Self-Evolving Framework for Resilient AI Systems

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha

ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving

TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms

SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud

StreamWise: Serving Multi-Modal Generation in Real-Time at Scale

Sherlock: Reliable and efficient workflow execution