Sliding-Window Attention

Follow this topic Ask about this topic

Sliding-window attention studies how to process long sequences by letting each token attend mainly to a fixed, nearby window, which can make computation and KV-cache use scale more gently with sequence length. Approaches include causal windows with attention sinks, shifted windows for cross-window communication, and hybrid models that reserve some layers or heads for global attention; distillation, reinforcement learning, and recurrent memory are also used to retain information beyond the window. The method is applied in language modeling, reasoning, speech generation, document processing, and vision, with evaluations spanning long-context retrieval, reasoning benchmarks, and generation quality. Its central tension is that smaller windows improve efficiency but can weaken long-range recall, so research asks which information or global pathways are needed to preserve quality and support length extrapolation.

Latest papers

24 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Oct 14, 2026

Speaking Longer Than Learned: Training-Free Long-Form Generation for Full-Stream Text-to-Speech

Recent full-stream text-to-speech (TTS) models enable low-latency personalized synthesis as input text arrives. However, sustaining generation beyond the lengths seen during training without additional training remains largely unexplored. We systematically analyze VoXtream2, which extends generation by periodically discarding past context while retaining the acoustic prompt. We find that this strategy does not prevent degradation: pronunciation accuracy deteriorates near the end of the training range due to the range of positions in which the model operates rather than the loss of past context, while speaker similarity gradually declines throughout generation. Based on these findings, we propose two training-free modifications that reduce the attention window and strengthen attention to the acoustic prompt. Experiments show that these modifications preserve pronunciation accuracy and speaker similarity throughout long-form generation while retaining the naturalness of the original model. Ablations further show complementary effects of the two modifications.

Jeseung Lim, Jiseong Woo, Heeseung Kim

Department of Physics, University of Seoul, Seoul, Republic of Korea · Department of AI, University of Seoul, Seoul, Republic of Korea

Long-Form TTS Synthesis TTS Synthesis Streaming TTS Synthesis Length Generalization Sliding-Window Attention TTS Evaluation

Oct 12, 2026

FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation

Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored, while hybrid architectures that add full attention for better recall incur quadratic sequence cost. Alternatively, sparse attention with continued pretraining (CPT) can extend the effective context length. Generalization beyond the trained length remains challenging, however, and CPT can be costly. We introduce FreeSolo, a native sparse attention mechanism with a short-range sliding window branch and a long-range branch that selects keypoint cells for direct token attention. Its linear-time variant, FS-L, learns to prune the prefix before query-dependent selection through short CPT. FS-B searches balanced trees with

O(N\log^2 N)

algorithmic cost including radix-sort construction. FreeSolo demonstrates better zero-shot length extrapolation than the baselines without long-context fine-tuning.

Zekun Shi, Alastair James Arthur Price

National University of Singapore · Sea AI Lab, Singapore · University of Toronto

Long-Context Language Modeling Long-Context Modeling Sparse Attention Sliding-Window Attention

Oct 6, 2026

Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation

Diffusion Transformers (DiTs) have achieved strong performance in image and video generation, but the quadratic complexity of full attention makes high-resolution generation computationally expensive. Window attention offers an efficient alternative, yet existing methods face a practical trade-off: partitioned window attention typically achieves computational efficiency consistent with its theoretical complexity. However, isolated windows block cross-window interaction, often introducing visible grid-like artifacts in the generated results. Fine-grained sliding-window attention effectively restores interactions across neighboring windows and improves visual quality. However, its irregular computation patterns create a substantial gap between theoretical and practical speedups and require specialized kernels tailored to each hardware backend. To tackle these challenges, we propose BASA, a backend-agnostic sparse attention, which brings the best of both worlds: visual quality and practical acceleration. Specifically, BASA replaces visual self-attention with shifted local-window attention. By introducing a structured window-shifting scheme across DiT blocks, we allow tokens divided by window boundaries in one layer to communicate in the following layers, thereby achieving global information exchange and eliminating window-induced visual artifacts. Notably, our design introduces no additional irregular operators or customized kernels, making it readily deployable on existing attention backends and closing the gap between theoretical sparsity and practical acceleration. Experiments demonstrate that BASA achieves measured speedups exceeding 90% of the theoretical estimates on FLUX and delivers a 4.52

\times

attention speedup on Wan while maintaining competitive generation quality. Codes are publicly available at: https://github.com/lama0110/BASA.

Liao Ma, Jiayi Song, Yunfeng Wu +2

School of Artificial Intelligence, Shanghai Jiao Tong University · School of Data Science, Fudan University · School of Computing and Data Science, The University of Hong Kong

Video Diffusion Models Diffusion Transformer Diffusion-Based Image Generation Sparse Attention Sliding-Window Attention Diffusion Model Inference Acceleration

Sep 29, 2026

How Local Mixing Encodes Relative Position in Global NoPE Attention

The attention operation is naively position invariant. However, positional information is fundamental to natural language, and therefore a variety of explicit position encodings have been developed in transformer-based models, such as rotary position encoding (RoPE). Although explicit position encodings have long been assumed to be required, recent methods that interleave local mixing layers, such as sliding window attention (SWA) and gated linear attention, while not encoding position (NoPE) in global attention layers has recently been shown to be successful at scale. How and why this approach works is not well-understood. In this paper, we develop an explanation of how hybrid models of this sort can implicitly encode position at global NoPE layers. Supported by both theoretical and empirical evidence, our central argument is that SWA and gated linear attention induce a recency bias in the residual stream that propagates to, and is selected by, the global attention logits. Moreover, in contrast to the implicit position encodings found in models with only global NoPE attention, in which positional information arises solely from the causal mask, the recency bias in hybrid models can be maintained across long sequences. In addition to deepening our understanding of how hybrid models encode position, these findings may provide insights for how to encode position in a way that can extrapolate to longer sequence lengths indefinitely.

Cutter Dawes, Nick Alonso, Tom Figliolia +1

Zyphra Research

Gated Attention Positional Encoding Sliding-Window Attention Hybrid Attention

Sep 28, 2026

Thinking Outside the Box: Retention and Transmission of Information in Sliding-Window KV Inference

Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional training, while its KV-cache memory remains fixed as more tokens are processed. Because cached states are computed in the context of earlier tokens, they may carry information from beyond the current window and transmit it to later states. This study presents a series of experiments using five open-weight models spanning Qwen, Llama, Mistral, and Muse Glimmer. We investigate whether information originating outside the immediate context window can persist through a rolling KV cache and remain useful for retrieval. Initial results show that retaining previously computed states improves retrieval across the models tested compared with recomputing the final fixed window from raw tokens. We then measure how far this effect extends and find that Muse Glimmer and Mistral 7B show the strongest latent information relay: they can recover information even after the relevant source tokens have left the cache. Both models incorporate sliding-window attention in their published architectures, an association that motivates testing whether training with sliding windows promotes more reliable information retention.

Timothy DeLise, Seth Cromelin

Long-Context Language Model Inference KV-Cache Reuse Sliding-Window Attention

Aug 28, 2026

Sliding-window beats linear attention

Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy: every new token costs more than the previous one, and its keys and values must be stored in memory indefinitely, which is unsustainable. Two main lines of work address this: compressing the KV cache, e.g., by evicting or quantizing keys and values, and retrofitting LLMs to use Linear Attention, which replaces the KV cache with a fixed-size state. Retrofitting has attracted a lot of attention, given its promise to solve the quadratic scaling problem with state-of-the-art performance at low cost. However, it has not been properly compared to the simplest form of KV-cache eviction: Sliding Window Attention (SWA) with attention sinks. In this work, we show that SWA with sinks performs as well or better than most retrofitted Linear Attention models across multiple LLMs and downstream tasks, with the largest gains on long-context and generative tasks. On long-context reasoning tasks (Needle-in-a-Haystack and BABILong), SWA achieves massively higher performance (2 to 10 times higher than linear attention). SWA requires no additional training, is extremely fast, and requires little memory, making it an extremely cheap and reliable solution. When the training budget is limited, switching to SWA is a much more effective way to reduce inference memory cost than retrofitting linear attention. Linear attention models have shown promise, but they require training from scratch or extensive retrofitting to reap their architectural benefits and come close to SWA.

Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron +1

Microsoft Applied Sciences Group (ASG) · Independent

Linear Attention KV Caching LLM Inference Acceleration Long-Context Inference Attention Sinks Sliding-Window Attention+1

Aug 26, 2026

Prefix Sliding for efficient test-time scaling

Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer when solving a problem. As models keep the entire reasoning trace in memory via full attention, hard tasks that need long thinking can be prohibitively expensive. However, we find most intermediate reasoning tokens lose importance as the model continues reasoning. This calls into question whether retaining them is worth the cost. Based on this insight, we propose Prefix Sliding, which discards tokens during reasoning that are not part of the prefix or the window of the last few thousand tokens. The prefix has key instructions and tools available to the model, while the most recent tokens are the current reasoning the model is working on. This caps the total memory requirement regardless of how long the model reasons, allowing for efficient long-horizon test-time scaling. Without training, Prefix Sliding can make existing models 3x faster while maintaining performance. Training with Prefix Sliding using reinforcement learning can achieve better performance by enabling scaling to reasoning traces beyond a hundred thousand tokens. Ablations show Prefix Sliding outperforms summarizing intermediate tokens or vanilla sliding window. Our code is at https://github.com/Muennighoff/prefix-sliding

Niklas Muennighoff, Zhengyang Wang, Zeyi Chen +15

Stanford University · University of California at Santa Barbara · University of Washington +1

LLM Inference Efficiency Test-Time Scaling Sliding-Window Attention

Aug 25, 2026

Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures

The growing adoption of large language models (LLMs) has raised increasing concerns about the energy consumption and environmental impact of inference. This paper presents a systematic empirical study of decode-phase energy consumption across representative open-source LLMs employing Multi-Head Attention (MHA), Grouped Query Attention (GQA), and Grouped Query Attention with Sliding Window Attention (SWA) to characterize how attention architecture influences decode-phase energy consumption under varying inference workloads. We evaluate four models across different context lengths, batch sizes, and generation workloads while measuring GPU energy using NVIDIA hardware counters. We examine the effects of context length, attention mechanism, Key-Value (KV) cache growth, and batching on decode-phase energy consumption. Results show that attention mechanism is the primary factor governing how decode energy scales with context length. MHA models exhibit substantially steeper energy growth than GQA models, whereas GQA with SWA maintains nearly constant energy consumption. We further show that model size primarily determines absolute energy consumption, while batching reduces both energy per generated token and request latency by up to 87%. These findings provide practical guidance for selecting energy-efficient LLM architectures and inference configurations.

Molka Chkir, Syed Muhammad Danish, Jos Höll +1

Algoma University, Brampton, Canada · School of Informatics, Reutlingen University, Reutlingen

Energy-Aware LLM Inference LLM Inference Efficiency Long-Context Language Model Inference Grouped-Query Attention Sliding-Window Attention

Aug 3, 2026

Maglev: Sliding Recurrent Memory

We introduce \ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training. \ours{} consists of two coupled models: a prefiller

Q

, which leverages full attention\footnote{In practice, we use interleaved full and sliding-window attention for

Q

, as this yields stronger performance. The essential requirement is that

Q

be more expressive than

P

, with access to the full history.} to produce memory targets

m'_t

, and a decoder

P

, which uses only sliding-window attention and recurrent K/V injection to produce decoder memories

m_t

for next-token prediction. We train \ours{} with a memory consistency loss that aligns

m_t

with

m'_t

, allowing inference to use

P

alone. Empirically, \ours{} improves validation loss and downstream pretraining benchmarks over sliding-window and latent recurrent transformer baselines. Moreover, sharing parameters between

P

and

Q

reduces parameter memory while preserving most of the gains.

Bo Liu, Qiang Liu

The University of Texas at Austin

Memory-Augmented Language Models Next-Token Prediction Recurrent Transformers Language Modeling Sliding-Window Attention Autoregressive Transformer

Jul 26, 2026

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Scalable Matrix Extension (SME). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming encoder, a temporal decoder, and a depth decoder, that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures, while causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10 ms per generation step, about 16x faster than real time, with a peak runtime memory of only 21 MB and 329 MB of on-device assets, enabling continuous streaming synthesis of 20-320 seconds of audio. This constant, small footprint replaces the linear and quadratic memory scaling of conventional transformer- and GAN-based approaches. Ablation studies validate the key architectural components, and audio quality assessment confirms that the architecture maintains synthesis fidelity while achieving efficiency gains over existing methods. Operating at a 1-billion-parameter activation size within AFM 3 Core Advanced, it improves Mean Opinion Score by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device text-to-speech system.

Dongseong Hwang, Prasanth Yadla, Kaan Elgin +8

Apple

TTS Synthesis Streaming TTS Synthesis Sliding-Window Attention

Jul 23, 2026

Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context

Speculative decoding accelerates autoregressive generation by having a draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP) draft head, assumed to be cheap beside verification. A shipped full-attention MTP head can become disproportionately expensive beside a hybrid target at long context. The head attends over the full KV cache for each of

γ

draft forwards per decode step, while only 9-25% of target layers retain full attention, so a single draft layer can issue context reads at a rate comparable to the whole target. On hard, low-acceptance workloads, deep native MTP becomes net-negative: slower than no speculation. We apply a StreamingLLM-style window plus attention sink to the draft only (Windowed-MTP); target verification remains full-context, so the target distribution is preserved. The intervention is training-free and drop-in. On three models from two hybrid families (Gated DeltaNet and Mamba2) at 1M context on one GPU in SGLang, it provides an acceptance-free 1.28-1.44x per-decode-step speedup over native MTP. The speedup grows with context; at matched acceptance, TPOT improves by the same factor. The window removes most of the draft's working set, and a compact ring buffer converts that reduction into physical capacity: it reclaims the otherwise dead draft pool, a measured 7.7-11.1% of total KV at 1M, making room for one additional concurrent 1M request in the Qwen-35B batch sweep.

Alagappan Valliappan

NVIDIA

Multi-Token Prediction Long-Context Language Model Inference Speculative Decoding LLM Inference Acceleration Sliding-Window Attention

Jun 26, 2026

NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation

Hybrid attention models that mix full and sliding-window attention across layers offer a promising approach to efficient long-context inference, but the critical question of which layers should retain full attention remains unsolved. Existing methods use either fixed periodic patterns or attention-based heuristics that may not capture what matters for downstream accuracy. We propose NLL-guided layer selection, a training-free method that directly measures each layer's importance by computing the negative log-likelihood degradation on answer tokens when that layer uses sliding-window instead of full attention. On LongMemEval with Qwen3-4B, our method achieves 64.6% accuracy using only 1/4 full-attention layers, matching the 1/2-FA periodic baseline (65.0%) while halving the computational budget. NLL-guided selection outperforms the SWAA-reported periodic 1/4-FA baseline by 10.4 percentage points and a matched LightTransfer-style baseline by 26.4 percentage points. De-confounding analysis shows the signal is consistent with long-range attention needs rather than generic layer sensitivity. The method requires only

\sim

15 minutes of one-time calibration, advancing the efficiency-accuracy Pareto frontier for long-context LLM deployment.

Qiong Tang, Xiangkun Hu, Xiangyang Liu +2

FARS

Long-Context Language Model Inference Sliding-Window Attention Attention Mechanisms Hybrid Attention

Jun 22, 2026

Unlimited OCR Works

Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a large language model (LLM) as the decoder allows the model to leverage the prior distribution of language, leading to improved OCR performance. However, the downside is equally evident: as the output sequence lengthens, the accumulated KV cache drives up memory consumption and progressively slows down generation. This stands in stark contrast to humans, who exhibit no such decline in efficiency during long-horizon copying tasks. In this technical report, we propose Unlimited OCR, a model designed to emulate human parsing working memory. Taking DeepSeek OCR as the baseline, we replace all attention layers in the decoder with our proposed Reference Sliding Window Attention (R-SWA), which reduces attention computation costs while maintaining a constant KV cache throughout the entire decoding process. By combining the high compression rate of DeepSeek OCR's encoder with our constant KV cache design, Unlimited OCR can transcribe dozens of pages of documents in a single forward pass under a standard maximum length of 32K. More importantly, R-SWA is a general-purpose parsing attention mechanism - beyond OCR, it is equally applicable to tasks such as ASR, translation, etc. Codes and model weights are publicly available at http://github.com/baidu/Unlimited-OCR.

Youyang Yin, Huanhuan Liu, YY +14

Baidu Inc.

Efficient Transformer Inference Long-Context Language Model Inference Sliding-Window Attention Optical Character Recognition

Jun 16, 2026

ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation

Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely on hand-crafted rules or simple post-hoc heuristics for FA/SWA allocation and offer limited analysis of the attention behaviors underlying these designs. We propose Controllable Sparsity in Hybrid Attention (ConSA), a framework that learns optimal FA/SWA assignment under a user-specified sparsity target. ConSA employs L0 regularization to learn binary masks selecting between FA and SWA for each attention unit, while an augmented Lagrangian constraint enforces the target sparsity at either layer or KV-head granularity. We evaluate ConSA on two LLMs at the 0.6B and 1.7B scales. Learned allocations consistently outperform rule-based baselines, with KV-head-wise allocation yielding clear gains over layer-wise allocation. The learned patterns place SWA in the bottom layers and concentrate FA into contiguous middle-layer blocks, diverging from evenly interleaved patterns in rule-based methods. This structure persists across model scales, sparsity levels, and allocation granularities, revealing a fine-grained spectrum of intrinsic attention behaviors that underlies the learned allocation.

Yao Chen, Yinqi Yang, Junyuan Shang +6

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · Baidu Inc.

LLM Inference Acceleration Sparse Attention Sliding-Window Attention Hybrid Attention

Jun 13, 2026

Rethinking the Role of Efficient Attention in Hybrid Architectures

Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent sequence mixers. However, how these efficient modules shape model capabilities remains poorly understood. To address this gap, we conduct a systematic analysis across hybrid architectures from three perspectives: scaling behavior, mechanism analysis, and architecture design. First, from a scaling perspective, we find that efficient-attention design primarily affects how fast long-context capability emerges, while different hybrids eventually converge to comparable long-context performance under sufficient training. Second, mechanistically, we show that long-range retrieval is mainly carried by full attention, whereas efficient attention shapes its optimization trajectory. This explains a counter-intuitive phenomenon we call Large-Window Laziness: larger SWA windows can delay the formation of retrieval heads in full-attention layers. Third, guided by this mechanism, we show that applying NoPE to only the full-attention layers of a small-window SWA hybrid substantially improves long-context performance with negligible impact on short-context performance.

Ziqing Qiao, Yinuo Xu, Chaojun Xiao +6

1Tsinghua University · 2OpenBMB

Attention Head Analysis Long-Context Modeling Efficient Attention Sliding-Window Attention Attention Mechanisms Hybrid Attention

Jun 10, 2026

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning

The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length. To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL). We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajectories to better match SWA. Experiments on mathematical reasoning benchmarks show that this recipe substantially narrows the gap between SWA and SA, recovering much of the accuracy lost during SWA conversion while preserving the efficiency benefits of linear-complexity attention. Our central contribution is the empirical finding that RL changes the conclusion one would draw from conversion and SFT alone about SWA's viability for math reasoning.

Kai Liu, Peijie Dong, Xinchen Xie +5

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · Shanghai AI Laboratory · Hong Kong University of Science and Technology (Guangzhou)

RL for Language Model Reasoning LLM Inference Acceleration Sliding-Window Attention RL Fine-Tuning LLM Mathematical Reasoning

Jun 1, 2026

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

Positional encoding (PE) is widely viewed as necessary for transformers to process ordered sequences: without them, the next-token map appears permutation-invariant in its context tokens. This intuition underlies all prior universality results, which rely on positional information to prove that transformers with chain-of-thought can perform arbitrary computation, i.e., they are Turing complete. We revisit this belief in the regime most relevant to long-form reasoning, where generation proceeds through a finite sliding context window. Our opening perception is that the window mechanism itself (mildly) breaks the permutation symmetry. To distill and precisely capture the degree of this added expressiveness, we introduce an abstract autoregressive model, the HIST model, in which each update depends only on constant-size internal state and the token-count histogram within the current window. We prove that this HIST model is Turing complete by showing that the evolution of the window can reveal the token that has just left the window, which suffices to simulate Turing-complete Post machines. We then construct a sliding-window transformer over a constant-size token alphabet, without PE, and show that it can simulate the HIST model. Our result demonstrates that positional encodings are not indispensable for transformers to perform universal computation: The window sliding itself already breaks permutation symmetry and captures sufficient positional information.

Qian Li, Xinyu Mao, Shang-Hua Teng

Shenzhen Research Institute of Big Data · University of Southern California

Transformer Expressivity Transformer Positional Encoding Sliding-Window Attention

May 27, 2026

Periodic RoPE for Infinite Context LLMs

The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extended context windows to 1M and beyond, model performance degrades when sequence length exceeds the pre-trained range of positional encodings (e.g., RoPE), i.e., position exhaustion. This fundamental limitation must be overcome to achieve a truly infinite context. To address it, we propose Periodic RoPE (P-RoPE), a positional encoding mechanism designed to circumvent this exhaustion. It operates in conjunction with sliding window attention (SWA) to capture local dependencies and relative positions within each window. This local layer is then complemented by a global attention layer with No Positional Encoding (NoPE), enabling unbounded interaction across the entire sequence without positional constraints. By stacking these two types of layers, the model avoids the need for positional extrapolation to generalize longer and theoretically supports an infinite context window. Empirical results show that our model, MiniWin, outperforms MiniMInd with standard GPT architectures in long-context efficiency and stability. Our work provides a possible pathway toward LLMs with genuine infinite-context understanding. The code is available at https://github.com/Cominder/miniwin.

Simin Huo

Shanghai Jiao Tong University

Rotary Positional Embeddings Long-Context Language Modeling Language Modeling Sliding-Window Attention

Apr 7, 2026

Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating

We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT), augmented by input-dependent gating. Self-attention is decomposed into consecutive width-wise and height-wise retention passes within each shifted window, where per-head exponential decay masks provide a two-dimensional locality prior without learned positional biases. Two variants are proposed.Gated-SwinRMT-SWAT substitutes softmax with sigmoid activation, implements balanced ALiBi slopes with multiplicative post-activation spatial decay, and gates the value projection via SwiGLU; the Normalized output implicitly suppresses uninformative attention scores. Gated-SwinRMT-Retention retains softmax-normalized retention with an additive log-space decay bias and incorporates an explicit G1 sigmoid gate -- projected from the block input and applied after local context enhancement (LCE) but prior to the output projection~

W_O

-- to alleviate the low-rank

W_V \!\cdot\! W_O

bottleneck and enable input-dependent suppression of attended outputs. We assess both variants on Mini-ImageNet (

224{\times}224

, 100 classes) and CIFAR-10 (

32{\times}32

, 10 classes) under identical training protocols, utilizing a single GPU due to resource limitations. At

{\approx}77

--

79

,M parameters, Gated-SwinRMT-SWAT achieves

80.22\%

and Gated-SwinRMT-Retention

78.20\%

top-1 test accuracy on Mini-ImageNet, compared with

73.74\%

for the RMT baseline. On CIFAR-10 -- where small feature maps cause the adaptive windowing mechanism to collapse attention to global scope -- the accuracy advantage compresses from

+6.48

,pp to

+0.56

,pp.

Dipan Maity, Suman Mondal, Arindam Roy

Student Kolkata, West Bengal, India · Department of Computer Science Yogoda Satsanga Palpara Mahavidyalaya West Bengal, India · Department of Computer Science & Application Prabhat Kumar College Contai West Bengal, India

Vision Transformer Gated Attention Image Classification Sliding-Window Attention

Apr 7, 2026

BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs

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 level via static rankings from local to global. Layer-level schemes ignore that local and global dependencies are routed through heads within the same layer, while static head-level rankings suffer from entanglement: a head's local/global behavior can change after hybridization. We propose BOSCH, Black-box Binary Optimization for Short-context Head Selection, a training-free method that formulates the problem as a Large Neighborhood Search and decomposes it into three subproblems: (i) layer-importance detection via small-budget black-box probes, (ii) adaptive per-layer SWA-ratio assignment based on these sensitivities, and (iii) grouped head-level optimization within ratio buckets. Extensive experiments on 4 LLMs ranging from 1.7B to 30B parameters, across 4 SWA ratios, show that BOSCH consistently outperforms layer-level heuristics and 6 strong static head-level methods, with larger gains at higher SWA ratios. Under continual pretraining, BOSCH recover original long-context performance faster and to a higher level. Analysis of the selected heads reveals substantial turnover for BOSCH across different SWA ratios, underscoring the importance of performing head-level selection for each target ratio rather than relying on fixed locality rankings.

Abbas Ghaddar, Ivan Kobyzev, Boxing Chen +1

Huawei Noah’s Ark Lab, Montreal Research Center, Canada

Hybrid Attention LLM Inference Acceleration Sliding-Window Attention

Apr 1, 2026

Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention

The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest path of only 4.4 hops. Despite being highly structured at the circuit level, the network's long-range connections are broadly distributed across brain regions, functioning as stochastic shortcuts that enable efficient global communication. Inspired by this observation, we propose Stochastic Attention (SA), a drop-in enhancement for sliding-window attention (SWA) that applies a random permutation to the token sequence before windowed attention and restores the original order afterward. This transforms the fixed local window into a stochastic global one within the same

O(nw)

per-layer budget. Through depth, independently sampled permutations yield exponentially growing receptive fields, achieving full sequence coverage in

O(\log_w n)

layers versus

O(n/w)

for SWA. We validate SA in two settings: pre-training language models from scratch, where a gated SA + SWA combination achieves the best average zero-shot accuracy, and training-free inference on Qwen3-8B and Qwen3-30B-A3B, where SA consistently outperforms SWA and matches or exceeds Mixture of Block Attention at comparable compute budgets. These results suggest that connectome-inspired stochastic routing is a practical primitive for improving the expressivity of efficient attention, complementary to existing linear and sparse approaches.

Zehao Jin, Yanan Sui

Tsinghua University

Efficient Attention Sliding-Window Attention

Mar 27, 2026

Switch Attention: Towards Dynamic and Fine-grained Hybrid Transformers

The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales quadratically with the sequence length, serving as a major bottleneck in long-context language modeling. Sliding window attention restricts the context length for better efficiency at the cost of narrower receptive fields. While existing efforts attempt to take the benefits from both sides by building hybrid models, they often resort to static, heuristically designed alternating patterns that limit efficient allocation of computation in various scenarios. In this paper, we propose Switch Attention (SwiAttn), a novel hybrid transformer that enables dynamic and fine-grained routing between full attention and sliding window attention. For each token at each transformer layer, SwiAttn dynamically routes the computation to either a full-attention branch for global information aggregation or a sliding-window branch for efficient local pattern matching. An adaptive regularization objective is designed to encourage the model towards efficiency. Moreover, we adopt continual pretraining to optimize the model, transferring the full attention architecture to the hybrid one. Extensive experiments are conducted on twenty-three benchmark datasets across both regular (4K) and long (32K) context lengths, demonstrating the effectiveness of the proposed method.

Yusheng Zhao, Hourun Li, Bohan Wu +5

State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University, Beijing, China · Contribution during internship at Huawei Technologies Co., Ltd. · Huawei Technologies Co., Ltd.

Hybrid Transformer Architectures Hybrid Attention Long-Context Language Modeling Conditional Computation Sliding-Window Attention

Mar 24, 2026

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new challenge: each window is processed independently, leading to semantic discrepancy across windows. To address this issue, we propose Global-Local Aligned CLIP~(GLA-CLIP), a framework that facilitates comprehensive information exchange across windows. Rather than limiting attention to tokens within individual windows, GLA-CLIP extends key-value tokens to incorporate contextual cues from all windows. Nevertheless, we observe a window bias: outer-window tokens are less likely to be attended, since query features are produced through interactions within the inner window patches, thereby lacking semantic grounding beyond their local context. To mitigate this, we introduce a proxy anchor, constructed by aggregating tokens highly similar to the given query from all windows, which provides a unified semantic reference for measuring similarity across both inner- and outer-window patches. Furthermore, we propose a dynamic normalization scheme that adjusts attention strength according to object scale by dynamically scaling and thresholding the attention map to cope with small-object scenarios. Moreover, GLA-CLIP can be equipped on existing methods and broad their receptive field. Extensive experiments validate the effectiveness of GLA-CLIP in enhancing training-free open-vocabulary semantic segmentation performance. Code is available at https://github.com/2btlFe/GLA-CLIP.

ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun +3

Sungkyunkwan University

Open-Vocabulary Semantic Segmentation Sliding-Window Attention Attention Mechanisms VLM Adaptation Vision-Language Alignment

Mar 17, 2026

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency.

Hanna Lee, Tan Dat Nguyen, Jaehoon Kang +1

Korea Advanced Institute of Science and Technology, Republic of Korea · Sungkyunkwan University, Republic of Korea

TTS Synthesis Self-Attention KV-Cache Management Sparse Attention Sliding-Window Attention Attention Mechanisms