arXiv:2608. 02938v1 Announce Type: cross Abstract: Graph attention normalizes neighborhood scores with softmax, the maximum-entropy choice under Shannon statistics.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper investigates KV‑cache eviction strategies for sparse‑attention models, showing that selecting the largest attention weights is nearly optimal—closing only a median 2–5 % of the gap to full attention. It further demonstrates that differences in performance between eviction methods largely stem from memory usage, with the new training‑free ContourKV allocator outperforming state‑of‑the‑art methods in most pairwise comparisons while matching their byte‑efficiency.
arXiv:2609.22770v2 Announce Type: cross Abstract: We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector...
arXiv:2609. 18145v1 Announce Type: new Abstract: Attention pays, at every layer and for every input, the cost of searching for whom to connect.
arXiv:2609.00892v1 Announce Type: new Abstract: Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforceme...
arXiv:2607. 07724v1 Announce Type: new Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks.
arXiv:2606. 13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale.