The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.
By Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos
The paper introduces LatentPort, a method that allows a language model to transfer its live memory to another model without requiring the receiver to reread the context. Experiments on a Qwen3.5 4B-to-9B sibling pair show that adding a Gated DeltaNet (GDN) persistent-state package reduces negative log‑likelihood by 0.747 nats/token and improves performance across 64 PG19 documents. The study also demonstrates that direct recurrent and convolution reuse outperforms learned GDN maps, and a 434,176‑parameter correction further narrows the performance gap to the native 9B model.
By Simon P. Villani
arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.
By Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya, Abhishek Gupta, Sandeep Kumar, Manoj Kumar
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
By Ke Wan, Chen Chen
arXiv:2608.30310v1 Announce Type: cross
Abstract: Hybrid large language models interleave full-attention layers with linear-attention layers to reduce the cost of long-context inference. This structu...
By Yirui Liu, Ruoling Qi, Xuaner Wu, Penghang Liu, Jian Chen
The paper introduces On‑Demand Attention (ODA), a decoding strategy that lets pretrained language models decide when to use global attention based on a lightweight recall head. ODA keeps the original model weights unchanged, only training the recall head, and can be implemented with GPU‑side conditional execution to reduce global reads. Experiments on Qwen, Gemma, and hybrid‑attention models show that ODA largely recovers performance lost by local attention while cutting the number of global attention operations.
By Haibo Feng, Ruiqi Liang, Hanyang Peng, Shiqi Yu
The paper introduces dQwen3.5, a family of diffusion language models derived from the hybrid-attention architecture of Qwen3.5 at 0.8B, 2B, 4B, and 9B parameters. It demonstrates that adapting a hybrid backbone—combining attention and RNN layers—can be more efficient than full-attention models, reaching a target training loss in roughly half the tokens. Across scales, dQwen3.5 exhibits full-attention-like behavior in any-order decoding and strong performance with parallel decoding.
By Anton Xue, Litu Rout, Aditya Akella, Adam Klivans, Sujay Sanghavi, Sanjay Shakkottai
The paper investigates where and how large language models encode signals that indicate answer correctness. By examining hidden states, token probabilities, residual-stream features, attention, and their combinations, the authors find that correctness signals are concentrated in the answer span and that different signal families complement each other. Fusing these signals improves robustness, especially under distribution shifts, and can be used to control retrieval in downstream tasks.
By Yuansen Liu, Yixuan Tang, Anthony Kum Hoe Tung
A game character should not have to reread its entire life before every conversation. For locally deployed language-model characters, however, revising a few memories can invalidate a long reusable pr...
DeltaS is a query‑agnostic, training‑free method for evicting key‑value cache entries in hybrid video‑language models that combine linear and full attention. It uses the change in the recurrent state of gated‑delta linear attention—called state drift—to decide which video chunks to keep, selecting those that induce larger normalized state changes. In experiments with a fixed memory budget, DeltaS outperforms position‑, attention‑, and key‑value‑based eviction signals, improving performance by 2.1 points on average across six long‑video benchmarks and 5.6 points on the longest benchmark, while adding only 1.9% of the forward‑pass cost.
By Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim, Moon Hwan Kim
The paper introduces dQwen3.5, a family of diffusion language models derived from the hybrid-attention architecture of Qwen3.5 at 0.8B, 2B, 4B, and 9B parameters. It demonstrates that adapting a hybrid AR backbone—combining attention and RNN layers—can be more efficient than full-attention models, reaching a target training loss in roughly half the tokens. Across scales, dQwen3.5 exhibits full-attention-like behavior in any‑order decoding and strong performance under parallel decoding.
arXiv:2606. 28876v2 Announce Type: replace-cross Abstract: We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence.
By Junyi Zou, Avrova Donz