arXiv:2608. 07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard.
By Yu Zhang
arXiv:2607. 10389v1 Announce Type: cross Abstract: A persistent interactive world model keeps its running state resident on the GPU that serves it: a multi-gigabyte attention cache, almost all of it rewritten at every generation step.
By Jin Li (Harvard University), Jiawei Chen
arXiv:2608. 08469v1 Announce Type: new Abstract: Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot naturally enter an active generation stream.
By Kaichen Zhang, Wei Huang, Keming Wu, Bo Li, Xiaojuan Qi
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
By Jianru Ding, Ryien Hosseini, Pouya Mahdi Gholami, Mingyuan Xiang, Henry Hoffmann
arXiv:2607. 17181v1 Announce Type: cross Abstract: Serverless multi-model LLM systems multiplex popularity-skewed model catalogs over shared GPU pools, yet typically schedule each request independently.
By Utopia Meng, Unicornt Zhao, Derek Li, Goalen Gao, Frank Du
arXiv:2606. 24470v1 Announce Type: new Abstract: A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds.
By Bojie Li, Noah Shi