arXiv:2608. 12348v1 Announce Type: cross Abstract: Streaming systems increasingly hand work to large language models (LLMs) -- writing pipelines, triaging alerts, reading logs -- and all of it assumes the model knows how event-time stream processing behaves.
arXiv:2608. 12348v2 Announce Type: replace-cross Abstract: Streaming systems increasingly hand work to large language models (LLMs): writing pipelines, triaging alerts, reading logs.
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.
arXiv:2607. 05690v2 Announce Type: replace Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn.
arXiv:2607. 05690v1 Announce Type: new Abstract: Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn.
arXiv:2607. 26448v1 Announce Type: cross Abstract: A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length grows.
arXiv:2607. 24667v1 Announce Type: new Abstract: A language model with a bounded working memory must repeatedly decide which stored items to keep.
arXiv:2607. 02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation.
arXiv:2607. 13048v1 Announce Type: cross Abstract: Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost.
arXiv:2607. 22962v1 Announce Type: new Abstract: LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning.
arXiv:2607. 21535v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel.
arXiv:2608. 08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said.
Speculative decoding accelerates autoregressive generation by having a cheap draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP/NEXTN) draft head under the assumption that the draft is negligibly cheap.