一作NeurIPS 2026Oral
Fractional State Space Transition for Long Sequence Modeling
Ivan Kobyzev · Abbas Ghaddar · Ali Nasiri-Sarvi · Lifeng Shang · Yufei CUI
长上下文与架构OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Ivan Kobyzev · Abbas Ghaddar · Ali Nasiri-Sarvi · Lifeng Shang · Yufei CUI
Abbas Ghaddar · Ivan Kobyzev · Boxing Chen · Yufei Cui
Post-training hybridization of large language models (LLMs) often replaces quadratic self-attention with sliding-window attention (SWA) to reduce KV cache usage and improve latency. Existing hybridization schemes are typically defined either at the layer level (e.g., interleaving) or at the head...