The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
arXiv:2608.30252v1 Announce Type: new Abstract: Long-context LLM applications such as document summarization and multi-turn agents require generation from prefixes spanning tens of thousands of token...
arXiv:2609.17943v1 Announce Type: new Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviates...
arXiv:2608. 26004v1 Announce Type: cross Abstract: Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions.
arXiv:2512. 22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel.
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.
arXiv:2606. 01019v1 Announce Type: cross Abstract: Large Language Model (LLM) generation remains expensive because autoregressive decoding calls the model once for each new token.