About Me
I am a final year Ph.D. student in the Computer Science Department at Carnegie Mellon University, advised by Zhihao Jia in the Catalyst Lab and Parallel Data Lab. I have spent the last two years at Snowflake AI Research, working with Samyam Rajbhandari and Aurick Qiao.
I build machine learning systems for large language models, spanning efficient inference and serving, speculative decoding, GPU kernel generation and optimization, and fine-tuning.
Education
-
Carnegie Mellon UniversityPhD in Computer ScienceExp. 2027 -
Tsinghua UniversityMS in Advanced Computing2023 -
Harvard UniversityBS in Electrical Engineering2021
Experience
-
Snowflake AI ResearchResearch InternMay 2024 - Aug. 2026 -
Whist TechnologiesSoftware EngineerSep. 2021 - Aug. 2022
Service
Reviewer for NeurIPS 2026, ICML 2026, MLSys 2026, TMLR 2026, ICLR 2025, SIGMOD 2024 (AEC), SOSP 2024 (AEC)
Research (all publications )
LLM Inference & Serving
Fast, cost-efficient LLM serving under strict SLOs, including speculative decoding that accelerates inference with no loss in output quality.
- SuffixDecoding (NeurIPS 2025 🌟, US Patent 2026 📜)
- SpecInfer (ASPLOS 2024 🔥)
- AdaServe (EuroSys 2026)
- SpecReason (NeurIPS 2025)
- OWL (arXiv 2025)
LLM Fine-Tuning
Memory-efficient fine-tuning and token-level co-serving of inference and training on shared GPUs.
GPU Kernels & Compilation
Generating, compiling, and orchestrating high-performance GPU kernels for ML workloads.
- FastKernels (arXiv 2026)
- Event Tensor (MLSys 2026)
- Korch (ASPLOS 2024)
Networking & Telemetry
Line-rate network telemetry collection that bypasses the CPU on the data path.
- Direct Telemetry Access (SIGCOMM 2023)
- Zero-CPU Collection (HotNets 2021)
🏆 Outstanding Paper ·
🌟 Spotlight ·
🔥 500+ citations ·
📜 Patent
Honors & Awards
Silver Reviewer Award, ICML
2026
Spotlight Presentation (Top 3.5%), NeurIPS
2025
Outstanding Paper Award (Top 0.5%), ACL
2024
Full-Ride Merit Scholarship, Tsinghua University
2021
Cum Laude with High Honors, Harvard University
2021