公開日 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 プロジェクト
公開日 Rollbaccine : Herd Immunity against Storage Rollback Attacks in TEEs David C. Y. Chu, Aditya Balasubramanian, Dee Bao, Natacha Crooks, Heidi Howard, Lucky E. Katahanas, Soujanya Ponnapalli International Conference on Management of Data | May 2026
公開日 Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference Zifan He, Rui Ma, Yizhou Sun, Jason Cong ICML 2026 | May 2026
公開日 XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms Tella Rajashekhar Reddy, Atharva Deshmukh, Liangcheng Yu, Chaojie Zhang, Mike Shepperd, Rohan Gandhi, A. Parayil, Srinivasan Iyengar, Ajay Manchepalli, Debopam Bhattacherjee 2026 ACM SoCC 2026 | May 2026
公開日 Argo: Efficient Importance Labeling for Enterprise Email Systems Siddhant Ray, Ganesh Ananthanarayanan, Kevin Chian, Yang Guo, C. Hill, Jack W. Stokes, Victor Wang, Junchen Jiang May 2026 arXiv | May 2026
公開日 UFO2: The Desktop AgentOS Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang Transactions on Machine Learning Research | May 2026 プロジェクト プロジェクト
公開日 Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants Bozhi You, Irene Wang, Z. Mustafaoglu, Abhinav Jangda, Angelica Moreira, Roshan Dathathri, Divya Mahajan, K. Pingali 9th MLSys Conference 2026 | May 2026
公開日 Nebula: Proving Machine Executions via Folding Schemes Arasu Arun, Srinath Setty May 2026 IEEE | May 2026
公開日 VeriCache: Turning Lossy KV Cache into Lossless LLM Inference Jiayi Yao, Samuel Y. Shen, Kuntai Du, Shaoting Feng, Dongjoo Seo, Rui Zhang, Yuyang Huang, Yuhan Liu, Shan Lu, Junchen Jiang May 2026 arXiv | May 2026
公開日 Skim: Speculative Execution for Fast and Efficient Web Agents Mike Wong, Kevin Hsieh, Suman Nath, Ravi Netravali May 2026 arXiv | May 2026