Hi there! 👋

I am a Ph.D. student in Computer Science at Purdue University, advised by Prof. Yi Ding. Before joining Purdue, I spent one year in Alibaba Cloud, building cloud-native deep learning infrastructure for distributed training and resource scheduling. Previously, I obtained both of my Master’s and Bachelor’s degrees in Computer Science from Shanghai Jiao Tong University (SJTU), where I was supervised by Prof. Ruhui Ma and Prof. Tao Song. I also worked with Prof. Yang Hua.

My research focuses on machine learning systems, with an emphasis on improving the efficiency and sustainability of Large Language Models (LLMs) through environmental impact evaluation, system-level optimizations, and the use of heterogeneous hardware platforms.

🚀 I am actively looking for internships. Feel free to reach out!

🔥 News

• 2025.08:  🎉🎉 Our work “Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner”, is accepted to EMNLP 2025 main conference! Many thanks to my collaborators!
• 2025.06:  🎉🎉 Our paper SCARF, a general framework for water-sustainable computing, is accepted to HotCarbon 2025! Congrats to all the authors!
• 2025.05:  🎉🎉 Our paper FUEL on benchmarking environmental impacts of LLM serving is accepted to ACL 2025 main conference! My deepest gratitude to my advisor!

📝 Publications

* denotes equal contribution

• ACL 2025 Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View
  Yanran Wu, Inez Hua, Yi Ding 📄 Paper · 💻 Code
  📰 Media Coverage: Green Software Foundation
• HotCarbon ‘25 Not All Water Consumption Is Equal: A Water Stress Weighted Metric for Sustainable Computing
  Yanran Wu, Inez Hua, Yi Ding 📄 Paper · 💻 Code
  📰 Media Coverage: Texas Public Radio · Green Software Foundation · Green Web Foundation
• EMNLP 2025 Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
  Bolian Li, Yanran Wu, Xinyu Luo, Ruqi Zhang 📄 Paper

• Preprint 2024 GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
  Tianyao Shi*, Yanran Wu*, Sihang Liu, Yi Ding 📄 Paper

• ICIP 2021 Fast and accurate scene parsing via bi-direction alignment networks
  Yanran Wu*, Xiangtai Li*, Chen Shi, Yunhai Tong, Yang Hua, Tao Song, Ruhui Ma, Haibing Guan 📄 Paper · 💻 Code

• ICIP 2021 Dynamic dual sampling module for fine-grained semantic segmentation
  Chen Shi*, Xiangtai Li*, Yanran Wu, Yunhai Tong, Yi Xu 📄 Paper

📖 Education

• Ph.D. in Computer Science, Purdue University
  2023 – Present   📍 West Lafayette, USA
  Advised by Prof. Yi Ding

• M.S. in Computer Science and Technology, Shanghai Jiao Tong University
  2019 – 2022   📍 Shanghai, China
  Advised by Prof. Ruhui Ma and Prof. Tao Song

• B.S. in Computer Science and Technology, Shanghai Jiao Tong University
  2015 – 2019   📍 Shanghai, China

💻 Experience

• Software Engineer, Alibaba Cloud
  Jun. 2022 – Jul. 2023   📍 Shanghai, China
  Worked on cloud-native infrastructure for distributed deep learning.

• Computer Vision Research Intern, SenseTime
  Jul. 2020 – Mar. 2022   📍 Shanghai, China
  Worked on multi-object detection for autonomous driving.

📚 Teaching

• Teaching Assistant, Purdue CS 37300: Data Mining and Machine Learning, Fall 2024
• Teaching Assistant, Purdue CS 53600: Data Communication and Computer Networks, Fall 2025