2027 NSDI The Streaming Batch Model for Efficient and Fault-Tolerant Heterogeneous Execution Frank Sifei Luan*, Ron Yifeng Wang*, Yile Gu, and 12 more authors In USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2027 Paper 2026 COLM ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Yile Gu*, Rohan Kadekodi*, Hoang Nguyen, and 3 more authors In Conference on Language Modeling (COLM), Oct 2026 To Appear Paper Website ICML Ekka: Automated Diagnosis of Silent Errors in LLM Inference Yile Gu, Zhen Zhang, Shaowei Zhu, and 4 more authors In International Conference on Machine Learning (ICML), Jul 2026 Paper Blog MLSys DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling Yi Pan, Yile Gu, Jinbin Luo, and 7 more authors In Conference on Machine Learning and Systems (MLSys), May 2026 Paper MLSys TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval Chien-Yu Lin*, Keisuke Kamahori*, Yiyu Liu, and 11 more authors In Conference on Machine Learning and Systems (MLSys), May 2026 Paper ICLR Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs Kan Zhu*, Tian Tang*, Qinyu Xu*, and 7 more authors In International Conference on Learning Representations (ICLR), Apr 2026 Paper 2025 SOSP Mitigating Application Resource Overload with Targeted Task Cancellation Yigong Hu, Zeyin Zhang, Yicheng Liu, and 4 more authors In ACM Symposium on Operating Systems Principles (SOSP), Nov 2025 Paper OOPSLA Scalable and Accurate Application-level Crash-Consistency Testing via Representative Testing Yile Gu*, Ian Neal*, Jiexiao Xu, and 7 more authors In ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA), Oct 2025 Paper OSDI NanoFlow: Towards Optimal Large Language Model Serving Throughput Kan Zhu, Yufei Gao, Yilong Zhao, and 11 more authors In USENIX Symposium on Operating Systems Design and Implementation (OSDI), Jul 2025 Paper ICLR Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models Keisuke Kamahori*, Tian Tang*, Yile Gu, and 2 more authors In International Conference on Learning Representations (ICLR), May 2025 Paper arXiv Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models Yile Gu, Yifan Xiong, Jonathan Mace, and 4 more authors arXiv preprint arXiv:2501.14170, 2025 Paper Blog arXiv Semantic Scheduling for LLM Inference Wenyue Hua*, Dujian Ding*, Yile Gu, and 4 more authors arXiv preprint arXiv:2506.12204, 2025 Paper arXiv AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic Systems Rohan Kadekodi*, Zhan Jin*, Keisuke Kamahori, and 5 more authors arXiv preprint arXiv:2510.00229, 2025 Paper 2024 SOSP Perseus: Removing Energy Bloat from Large Model Training Jae-Won Chung, Yile Gu, Insu Jang, and 3 more authors In ACM Symposium on Operating Systems Principles (SOSP), Nov 2024 Paper