Sparse Attention

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 200% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 160

May 4, 2026cs.LG

StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k

DeepSeek-V3.2 and V4 introduce Compressed Sparse Attention (CSA): a lightning indexer (a learned scoring projection over compressed keys) scores them, the top-k are selected per query, and a sparse attention kernel reads only those. Public CSA implementations materialize a [B, S, H_I, T] FP32 score tensor before the top-k reduction. With H_I=64 indexer heads and the V4-Flash compression ratio m=4, that intermediate is 256 GB at sequence length S=65,536, exceeding any single-GPU high-bandwidth-memory (HBM) budget. We present StreamIndex, a Triton implementation of the CSA pipeline whose central component is a chunked partition-merge top-k driver that never materializes the full intermediate. On synthetic-but-realistic V4-shaped inputs at the indexer-step (layer) level on a single NVIDIA H200, the materialize path runs out of memory (OOMs) at S=65,536 with V4-Flash dimensions; StreamIndex runs the same indexer to S=1,048,576 with 6.21 GB peak HBM, a 32x regime extension. Set-overlap recall against the materialize ground truth is bit-exact at small S where both fit; across three 5-point design-space sweeps (chunk size, key-tile size, top-k), mean recall rounds to 1.0000 with min recall at least 0.9980 in every cell. The chunked driver composes with TileLang's pipelined attention kernel: at S=262,144 with V4-Flash dimensions, the materialize indexer paired with TileLang attention OOMs while the chunked indexer paired with the same attention runs in 1.97 s at 18.56 GB peak. Our contribution targets the indexer step; we make no claim of a faster attention kernel or of real-checkpoint end-to-end behavior. Code: https://github.com/RightNow-AI/StreamIndex.

Jaber Jaber, Osama Jaber

RightNow AI

GPU Kernel Optimization Self-Attention Memory-Efficient Optimization Memory-Efficient Inference Efficient Attention Sparse Attention

May 3, 2026cs.LG

Stochastic Sparse Attention for Memory-Bound Inference

Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all

n_k

key and value vectors from KV cache. We present Stochastic Additive No-mulT Attention (SANTA), a method that sparsifies value-cache access by sampling

S \ll n_k

indices from the post-softmax distribution and aggregates only those value rows. This yields an unbiased estimator of the post-softmax value aggregation while replacing value-stage multiply-accumulates with gather-and-add. We introduce stratified and systematic sampling to design variance-reduced, GPU-friendly variants. Evaluated on Llama-3.1-8B-Instruct at 32k-token contexts, S

^2

ANTA matches baseline accuracy while achieving up to

1.5\times

decode-step attention-kernel speedup over FlashInfer and FlashDecoding on an NVIDIA RTX 6000 Ada. In batched long-context generation, these kernel gains translate to up to

1.25\times

end-to-end decode-latency speedup. Finally, we propose Bernoulli

qK^\mathsf{T}

sampling as a complementary technique to sparsify the score stage, reducing key-feature access through stochastic ternary queries. Both methods are complementary to upstream quantization, low-rank projection, KV-cache compression, and KV-cache selection methods. Together, they point toward sparse, multiplier-free, and energy-efficient inference. We open-source our kernels at: https://github.com/OPUSLab/SANTA.git

Kyle Lee, Corentin Delacour, Kevin Callahan-Coray +5

Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA · Department of Electrical and Computer Engineering, University of Michigan, Ann Arbor, MI, USA · Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA

GPU Acceleration Self-Attention KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration+1

Apr 30, 2026eess.IV

Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution

Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of standard feed-forward networks (FFNs). To address these challenges, we propose Spectral Dynamic Attention Network (SDANet), a framework designed to adaptively suppress redundant spectral interactions. SDANet integrates two key components: 1) Dynamic Channel Sparse Attention (DCSA) module that computes channel-wise correlations and selectively preserves the most informative attention responses through dynamic and data-dependent sparsification. 2) Frequency-Enhanced Feed-Forward Network (FE-FFN) that jointly models spatial and frequency-domain representations to enhance non-linear expressiveness. Extensive experiments on two benchmark datasets demonstrate that SDANet achieves state-of-the-art HISR performance while maintaining competitive efficiency. The code will be made publicly available at https://github.com/oucailab/SDANet.

Tengya Zhang, Feng Gao, Lin Qi +2

Sanya Oceanographic Institution, Ocean University of China, Sanya, China · State Key Laboratory of Physical Oceanography, Ocean University of China, Qingdao 266100, China · Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS 39762 USA

Hyperspectral Image Super-Resolution Hyperspectral Imaging Sparse Attention Image Super-Resolution

Apr 29, 2026cs.LG

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV storage to CPU memory. In practice, however, these algorithmic savings rarely translate into end-to-end system-level gains because sparse methods typically operate at different granularities and thus rely on ad hoc, per-algorithm implementations. At the same time, hierarchical KV storage introduces a new systems bottleneck: retrieving fine-grained, irregular KV subsets across the GPU-CPU boundary can easily erase the benefits of sparsity. We present SPIN, a sparse-attention-aware inference framework that co-designs the execution pipeline with hierarchical KV storage through three techniques: (1) a unified partition abstraction that maps different sparsity granularities onto a shared page-based KV substrate; (2) a locality-aware KV cache manager that dynamically sizes per-request HBM budgets and uses a GPU-friendly bucketed LRU policy to cut PCIe round-trips; and (3) a two-level hierarchical metadata layout sized to the active working set rather than the worst-case address space. Built on vLLM with three representative sparse attention algorithms, SPIN delivers 1.66-5.66x higher end-to-end throughput and 7-9x lower TTFT than vLLM, and reduces TPOT by up to 58% over the original sparse-attention implementations.

Zihan Zhao, Baotong Lu, Shengjie Lin +8

University of Virginia · Microsoft Research · Georgia Institute of Technology +1

LLM Serving KV-Cache Offloading KV Caching Long-Context Language Model Inference KV-Cache Management Sparse Attention

Apr 27, 2026cs.AR

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding

Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache, dramatically increasing bandwidth and computing pressure. Existing accelerators are primarily designed and evaluated for short contexts. They suffer from significant performance degradation when processing long contexts. To bridge this gap, we identify the major bottleneck and present a hardware accelerator for long context attention decoding via hardware-software co-design. On the software side, we propose dual-compression dynamic sparse attention. It combines ultra-low-precision quantization with feature sparsity to minimize prediction overhead. A hardware-friendly approximate Top-K selection further reduces filter complexity from

O(n \log k)

to

O(n)

. On the hardware side, we deeply optimize compute and memory access to tackle bottlenecks from intricate interplay between sparse attention and long contexts, and establish a performance model to derive the optimal co-design scheme. The resulting hardware adopts a fully pipelined parallel architecture and achieves

O(n)

efficiency even for long sequences. Experiments show that our design delivers

3.82\times

speedup and

74.19\times

energy efficiency over A100. Compared to SOTA accelerators, this is the first ASIC accelerator that efficiently supports long context inference, with at least

3.5\times

higher throughput and

2.08\times

better energy efficiency.

Wang Fan, Wei Cao, Xi Zha +5

Fudan University

Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention Attention Mechanisms

Apr 27, 2026cs.CV

SparseContrast: Dynamic Sparse Attention for Efficient and Accurate Contrastive Learning in Medical Imaging

We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-ray disease detection in low-data settings. Traditional contrastive learning methods rely on dense attention mechanisms, which are computationally expensive and often process redundant regions in medical images. To resolve this, SparseContrast introduces a sparse attention mechanism that selectively concentrates on diagnostically pertinent areas, markedly decreasing computational burden without compromising accuracy. The framework adaptively trims attention maps in the training phase, directed by a compact saliency predictor which concurrently optimizes sparsity and feature quality. This method not only speeds up training and inference by as much as 40% relative to dense attention benchmarks but also boosts diagnostic accuracy by focusing on areas of clinical importance. Moreover, the approach remains indifferent to the selection of backbone architecture, which permits its application to both convolutional and transformer-based models. Experiments show SparseContrast attains comparable or better performance in disease identification tasks with greater efficiency relative to current approaches. The proposed framework delivers a practical approach for implementing contrastive learning in medical imaging settings with limited resources, where computational efficiency and diagnostic accuracy are paramount.

Paarth Prasad, Ruchika Malhotra

Department of Software Engineering, Delhi Technological University

Contrastive Learning Chest X-Ray Classification Sparse Attention Medical Image Representation Learning

Apr 26, 2026cs.CL

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

DeepSeek-AI, Anyi Xu, Bangcai Lin +316

Mixture-of-Experts Language Models Long-Context Language Model Inference Long-Context Language Modeling LLM Inference Acceleration Sparse Attention Attention Mechanisms+1

Apr 25, 2026cs.CV

BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning

Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restricted information capacity of binary spike coding and the dense token interactions introduced by global self-attention. To address these challenges, this work proposes BSViT, a burst spiking-driven Vision Transformer featuring a Dual-Channel Burst Spiking Self-Attention (DBSSA) mechanism. DBSSA encodes queries with binary spikes and keys with burst spikes to enhance representational capacity. The value pathway adopts dual excitatory and inhibitory binary channels, enabling signed modulation and richer spike interactions. Importantly, the entire attention operation preserves addition-only computation, ensuring compatibility with energy-efficient neuromorphic hardware. To further reduce spike activity and incorporate spatial priors, a patch adjacency masking strategy is introduced to restrict attention to local neighborhoods, resulting in structure-aware sparsity and reduced computational overhead. In addition, burst spike coding is systematically integrated across the network to increase spike-level representational capacity beyond conventional binary spiking. Extensive experiments on both static and event-based vision benchmarks demonstrate that BSViT consistently outperforms existing spiking Transformers in accuracy while maintaining competitive energy efficiency.

Hongxiang Peng, Dewei Bai, Hong Qu

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China

Spiking Transformers Efficient ViTs Spiking Neural Networks Sparse Attention

Apr 24, 2026cs.LG

SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference

Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenecks at long sequences. A key challenge is to design foundation models that maintain performance and long-context efficiency with minimal training overhead. We introduce SpikingBrain2.0 (SpB2.0), a 5B model that advances both architecture and training efficiency of its predecessor. Our contributions are two-fold. (1) Architectural Innovation: We propose Dual-Space Sparse Attention (DSSA), an inter-layer hybrid of Sparse Softmax Attention (MoBA) and Sparse Linear Attention (SSE), achieving an improved performance-efficiency trade-off for long-context modeling. SpB2.0 further supports dual quantization paths: INT8-Spiking coding enables sparse event-driven computation, while FP8 coding accelerates inference on modern GPUs. (2) Enhanced Training Strategy: We develop an optimized Transformer-to-Hybrid (T2H) pipeline with dual conversion paths for LLMs and VLMs using curated open-source data. Empirically, SpB2.0-5B and SpB2.0-VL-5B recover most of the base Transformer (Qwen3-4B) capability with under 7k A100 GPU hours. SpB2.0 achieves a 10.13x TTFT speedup at 4M context and supports over 10M tokens on 8 A100 GPUs under vLLM, where full-attention models exceed memory limits. It also demonstrates strong cross-platform compatibility, enabling FP8 GPU inference (2.52x speedup at 250k) and efficient neuromorphic execution (64.31% sparsity, with 70.6% and 46.5% area and power reduction at 500MHz). Overall, SpikingBrain2.0 provides a practical pathway for lightweight, multimodal, spiking foundation models, highlighting the potential of combining brain-inspired mechanisms with efficient architectures for resource-constrained and edge scenarios.

Yuqi Pan, Jinghao Zhuang, Yupeng Feng +16

Institute of Automation, Chinese Academy of Sciences · The Hong Kong Polytechnic University · Beijing Key Laboratory of Brain-Inspired General Intelligence Large Model +1

Long-Context Language Model Inference Spiking Neural Networks Sparse Attention Neuromorphic Computing

Apr 24, 2026cs.LG

HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models

We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M << n is a small number of learned hub tokens. We demonstrate it in two from-scratch architectures: a Jamba-style hybrid and a 12-layer Transformer; retrofit into pretrained models is a tested negative case. HubRouter implements an encode-decode-score-council pipeline: M learned hubs cross-attend to all tokens, tokens project against hubs for routing fingerprints, a score head selects top-k tokens, and a sparse council attends only to the selected subset. We validate HubRouter in three settings. (1) Hub-Jamba yields a nominal 4.2% PPL improvement (200.2 vs 209.0, single seed; possibly within seed noise) and up to ~90x training throughput at sequence length 1024 in matched PyTorch-native baselines; an optimised baseline would narrow this to ~10-15x. (2) Graduated replacement of 25% of Transformer attention layers gives the best perplexity in our matched-budget sweep (268.0 vs 282.4 pure Transformer). (3) Hub-GPT provides strictly causal routing, achieving PPL 211.5 +/- 0.4 over 3 seeds (post council-causal fix); approximately 3 PPL worse than Jamba's 208.5 +/- 0.7, a measurable quality cost for avoiding O(n^2) computation. Post-fix, chunk size C has little effect; the pre-fix chunk-size benefit was an artifact of a bidirectional-council leak we found in adversarial review. A multi-seed hub-count sweep (~105 runs across M=1-32) reveals M=8-14 as the reliably-converging sub-band (4-5/5 seeds); M=6 is rescued to 5/5 by orthogonal regularization, while M>=20 shows increasing seed sensitivity. Companion paper arXiv:2603.20997 (Basu, 2026) defines the routing diagnostic task. Code and scripts will be released.

Abhinaba Basu

National Institute of Electronics and Information Technology (NIELIT)

Transformer Attention Language Modeling Sparse Attention Attention Mechanisms Sequence Modeling

Apr 23, 2026cs.CV

Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers

Recent breakthroughs in 3D generative modeling have yielded remarkable progress in static shape synthesis, yet high-fidelity dynamic 4D generation remains elusive, hindered by temporal artifacts and prohibitive computational demand. We present Sculpt4D, a native 4D generative framework that seamlessly integrates efficient temporal modeling into a pretrained 3D Diffusion Transformer (Hunyuan3D 2.1), thereby mitigating the scarcity of 4D training data. At its core lies a Block Sparse Attention mechanism that preserves object identity by anchoring to the initial frame while capturing rich motion dynamics via a time-decaying sparse mask. This design faithfully models complex spatiotemporal dependencies with high fidelity, while sidestepping the quadratic overhead of full attention and reducing network total computation by 56%. Consequently, Sculpt4D establishes a new state-of-the-art in temporally coherent 4D synthesis and charts a path toward efficient and scalable 4D generation.

Minghao Yin, Wenbo Hu, Jiale Xu +2

1The University of Hong Kong · 2ARC Lab, Tencent PCG

Diffusion Transformer 3D Shape Generation Sparse Attention

Apr 23, 2026cs.CV

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation

We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding latency. Sparse Forcing is motivated by an empirical observation in autoregressive diffusion rollouts: attention concentrates on a persistent subset of salient visual blocks, forming an implicit spatiotemporal memory in the KV cache, and exhibits a locally structured block-sparse pattern within sliding windows. Building on this observation, we propose a trainable native sparsity mechanism that learns to compress, preserve, and update these persistent blocks while restricting computation within each local window to a dynamically selected local neighborhood. To make the approach practical at scale for both training and inference, we further propose Persistent Block-Sparse Attention (PBSA), an efficient GPU kernel that accelerates sparse attention and memory updates for low-latency, memory-efficient decoding. Experiments show that Sparse Forcing improves the VBench score by +0.26 over Self-Forcing on 5-second text-to-video generation while delivering a 1.11-1.17x decoding speedup and 42% lower peak KV-cache footprint. The gains are more pronounced on longer-horizon rollouts, delivering improved visual quality with +0.68 and +2.74 VBench improvements, and 1.22x and 1.27x speedups on 20-second and 1-minute generations, respectively.

Boxun Xu, Yuming Du, Zichang Liu +7

Meta Superintelligence Labs · University of California, Santa Barbara · Work done at Meta

Autoregressive Diffusion Self-Attention Long-Horizon Video Generation Attention Control in Diffusion Models Sparse Attention KV-Cache Compression+3

Apr 22, 2026cs.CV

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose \textbf{DynamicRad}, a unified sparse-attention paradigm that grounds adaptive selection within a radial locality prior. DynamicRad introduces a \textbf{dual-mode} strategy: \textit{static-ratio} for speed-optimized execution and \textit{dynamic-threshold} for quality-first filtering. To ensure robustness without online search overhead, we integrate an offline Bayesian Optimization (BO) pipeline coupled with a \textbf{semantic motion router}. This lightweight projection module maps prompt embeddings to optimal sparsity regimes with \textbf{minimal runtime overhead}. Unlike online profiling methods, our offline BO optimizes attention reconstruction error (MSE) on a physics-based proxy task, ensuring rapid convergence. Experiments on HunyuanVideo and Wan2.1-14B demonstrate that DynamicRad pushes the efficiency--quality Pareto frontier, achieving \textbf{1.7

\times

--2.5

\times

inference speedups} with \textbf{over 80% effective sparsity}. In some long-sequence settings, the dynamic mode even matches or exceeds the dense baseline, while mask-aware LoRA further improves long-horizon coherence. Code is available at https://github.com/Adamlong3/DynamicRad.

Yongji Long, Shijun Liang, Jintao Li +1

University of Electronic Science and Technology of China · Shenzhen Institute for Advanced Study, UESTC · Computational Mathematics, Science, & Engineering at Michigan State University (MSU)

Video Diffusion Models Long-Horizon Video Generation Sparse Attention Diffusion Model Inference Acceleration

Apr 22, 2026cs.LG

Simplified Sparse Attention via Gist Tokens

Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components. We introduce Simplified Sparse Attention (SSA), a simpler approach to sparse attention that requires no architectural changes. Concretely, we first perform continued pretraining on sequences interleaved with gist tokens. We optimize the standard next-token loss as usual, but the gist tokens use an attention mask to restrict what parts of the context the language model can attend to; this teaches the model to pack each chunk's important information into the gist tokens. At inference time, SSA scores chunks via attention between the current query and the small set of gist tokens, selectively unfolding the top-k chunks by reintroducing their corresponding raw tokens. Since the query is scored only against the gist tokens, we avoid the memory-bandwidth cost associated with naive scoring against the full KV cache, without requiring the auxiliary KV cache approach used by sparse attention methods. On LongBench, SSA consistently outperforms compression and inference-time sparse-attention baselines under the same compression ratio. More strikingly, in retrieval-augmented generation, SSA can even outperform full attention after continued pretraining by over 5.7 points. We attribute this to the ability of SSA's selective unfolding, which concentrates attention on the query-relevant chunks and effectively filters out noise. SSA further extends to a hierarchical gist-of-gist variant (H-SSA) that achieves log-linear decoding complexity while maintaining or improving accuracy at high compression ratios up to 32x. The code is available at https://github.com/yuzhenmao/simplified-sparse-attention/.

Yuzhen Mao, Michael Y. Li, Emily B. Fox

Stanford University

Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention Attention Mechanisms

Apr 20, 2026cs.CV

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity or fail to adapt to heterogeneous token distributions across layers, leading to model performance degradation. We propose AdaCluster, a training-free adaptive clustering framework that accelerates the generation of DiTs while preserving accuracy. AdaCluster applies an angle-similarity-preserving clustering method to query vectors for higher compression, and designs a euclidean-similarity-preserving clustering method for keys, covering cluster number assignment, threshold-wise adaptive clustering, and efficient critical cluster selection. Experiments on CogVideoX-2B, HunyuanVideo, and Wan-2.1 on one A40 GPU demonstrate up to 1.67-4.31x speedup with negligible quality degradation.

Haoyue Tan, Shengnan Wang, Yulin Qiao +5

University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · 3Independent Researcher +2

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration

Apr 16, 2026cs.LG

AdaSplash-2: Faster Differentiable Sparse Attention

Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is

α

-entmax attention, a differentiable sparse alternative to softmax that enables input-dependent sparsity yet has lagged behind softmax due to the computational overhead necessary to compute the normalizer

τ

. In this paper, we introduce AdaSplash-2, which addresses this limitation through a novel histogram-based initialization that reduces the number of iterations needed to compute

τ

to typically 1--2. The key idea is to compute a coarse histogram of attention scores on the fly and store it in on-chip SRAM, yielding a more accurate initialization that enables fast forward and backward computation. Combined with a sparsity-aware GPU implementation that skips zero blocks with low overhead, AdaSplash-2 matches or improves per-step training time relative to FlashAttention-2 when block sparsity is moderate-to-high (e.g.,

>

60%), which often occurs at long-context lengths. On downstream tasks, models trained with our efficient

α

-entmax attention match softmax baselines at short-context lengths and achieve substantial gains in long-context settings.

Nuno Gonçalves, Hugo Pitorro, Vlad Niculae +4

Instituto Superior Técnico, Universidade de Lisboa · Instituto de Telecomunicações · Carnegie Mellon University +4

GPU Kernel Optimization Self-Attention Long-Context Modeling Efficient Attention Sparse Attention Attention Mechanisms

Apr 16, 2026cs.LG

Improving Sparse Autoencoder with Dynamic Attention

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for each neuron remains challenging in practice: excessive sparsity can lead to poor reconstruction, whereas insufficient sparsity may harm interpretability. While existing activation functions such as ReLU and TopK provide certain sparsity guarantees, they typically require additional sparsity regularization or cherry-picked hyperparameters. We show in this paper that dynamically sparse attention mechanisms using sparsemax can bridge this trade-off, due to their ability to determine the activation numbers in a data-dependent manner. Specifically, we first explore a new class of SAEs based on the cross-attention architecture with the latent features as queries and the learnable dictionary as the key and value matrices. To encourage sparse pattern learning, we employ a sparsemax-based attention strategy that automatically infers a sparse set of elements according to the complexity of each neuron, resulting in a more flexible and general activation function. Through comprehensive evaluation and visualization, we show that our approach successfully achieves lower reconstruction loss while producing high-quality concepts, particularly in top-n classification tasks.

Dongsheng Wang, Jinsen Zhang, Dawei Su +1

College of Computer Science and Software Engineering, Shenzhen University, China

Sparse Autoencoders Neural Network Interpretability Sparse Attention

Apr 8, 2026cs.LG

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA) offer a potential solution, existing methods typically rely on static allocation ratios that fail to accommodate the variable retrieval demands of different tasks. Furthermore, head-level dynamic sparsity often introduces severe computational load imbalance and synchronization long-tails, which hinder hardware acceleration during autoregressive decoding. To bridge this gap, we introduce Flux Attention, a context-aware framework that dynamically optimizes attention computation at the layer level. By integrating a lightweight Layer Router into frozen pretrained LLMs, the proposed method adaptively routes each layer to FA or SA based on the input context. This layer-wise routing preserves high-fidelity information retrieval while ensuring contiguous memory access, translating theoretical computational reductions into practical wall-clock speedups. As a parameter-efficient approach, our framework requires only 12 hours of training on 8

\times

A800 GPUs. Extensive experiments across multiple long-context and mathematical reasoning benchmarks demonstrate that Flux Attention achieves a superior trade-off between performance and inference speed compared with baseline models, with speed improvements of up to

2.8\times

and

2.0\times

in the prefill and decode stages.

Quantong Qiu, Zhiyi Hong, Yi Yang +5

School of Computer Science and Technology, Soochow University · Baidu Inc, China

Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention Attention Mechanisms Hybrid Attention

Apr 6, 2026cs.CV

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction. Although recent object-centric feed-forward methods produce robust, high-quality reconstructions, they still lag behind dense-view optimization in recovering fine-grained texture and appearance. We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering. To scale effectively, we adapt native sparse attention for 3D reconstruction with three key contributions: (1) an efficient coarse-to-fine pipeline that focuses computation on informative regions by predicting sparse high-resolution residuals; (2) a 3D-aware spatial routing mechanism that establishes accurate 2D-3D correspondences using explicit geometric distances rather than standard attention scores; and (3) a custom block-aware sequence-parallel strategy with an All-gather-KV protocol to balance dynamic, sparse workloads across GPUs. As a result, LSRM handles 20x more object tokens and >2x more image tokens than prior state-of-the-art (SOTA) methods. Extensive evaluations on standard novel-view synthesis benchmarks show substantial gains over the current SOTA, yielding >2.4dB higher PSNR and >40% lower LPIPS. Furthermore, when extending LSRM to inverse rendering, qualitative and quantitative evaluations on widely used benchmarks demonstrate consistent improvements in texture and geometry details, achieving an LPIPS that matches or exceeds that of SOTA dense-view optimization methods. Code and model weights are available on our project page.

Zhengqin Li, Cheng Zhang, Jakob Engel +1

Meta Reality Labs Research

Inverse Rendering 3D ViTs 3D Reconstruction Novel View Synthesis Sparse Attention Feed-Forward 3D Reconstruction

Mar 30, 2026cs.LG

HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention

Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.

Yufei Xu, Fanxu Meng, Fan Jiang +11

Xiaohongshu

Self-Attention LLM Inference Acceleration Efficient Attention Sparse Attention Attention Mechanisms

Mar 18, 2026cs.CL

Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We observe that most tokens do not require (Global) Attention over the entire sequence and can rely on local context. Based on this, we propose L2A (Learning To Attend), a layer that enables conditional (token-wise) long-range memory access by deciding when to invoke global attention. We evaluate L2A on Qwen 2.5 and Qwen 3 models, extending their effective context length from 32K to 128K tokens. L2A matches the performance of standard long-context training to within 3% while skipping Global Attention for

\sim

80% of tokens, outperforming prior baselines. We also design custom Triton kernels to efficiently implement this token-wise conditional Attention on GPUs, achieving up to

\sim

2

\times

improvements in training throughput and time-to-first-token over FlashAttention. Moreover, L2A enables post-training pruning of highly sparse Global Attention layers, reducing KV cache memory by up to 50% with negligible performance loss. Our code is released under Apache 2.0 at https://github.com/awslabs/hybrid-model-factory/tree/main/examples/research/L2A.

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato +4

Department of Electrical and Computer Engineering, Purdue University, USA · AWS Agentic AI, USA

Self-Attention Long-Context Language Modeling LLM Inference Acceleration Sparse Attention Attention Mechanisms

Mar 17, 2026cs.CL

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

Mar 16, 2026cs.CL

When Does Sparsity Mitigate the Curse of Depth in LLMs

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance in Pre-Layer Normalization, which can push deep blocks toward near-identity behavior. In this paper, we provide evidence that sparsity-like mechanisms can dampen variance propagation and are associated with improved depth utilization Our investigation covers two sources of sparsity: (i) implicit sparsity, which emerges from training and data conditions, including weight sparsity induced by weight decay and attention sparsity induced by long-context inputs; and (ii) explicit sparsity, which is enforced by architectural design, including key/value-sharing in Grouped-Query Attention and expert-activation sparsity in Mixtureof-Experts. Our claim is thoroughly supported by controlled depth-scaling experiments and targeted layer effectiveness interventions. Across settings, we observe a consistent relationship: mechanisms with reduced effective interaction density tend to exhibit lower output variance and better layer differentiation. We eventually distill our findings into a practical rule-of-thumb recipe for training depth-effective LLMs, yielding a notable 4.6 accuracy improvement on downstream tasks. Our results suggest that sparsity-like design choices are an important and previously underemphasized factor in effective depth scaling for LLMs. Code is available at https://github. com/pUmpKin-Co/SparsityAndCoD.

Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta +4

Max Planck Institute for Intelligent Systems · ELLIS Institute Tübingen · Tübingen AI Center +4

Grouped-Query Attention Language Model Scaling Sparse Attention

Mar 9, 2026cs.CV

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However, prior methods often either drop the remaining blocks, which incurs information loss, or rely on learned predictors to approximate them, introducing training overhead and potential output distribution shifting. In this paper, we show that the missing contributions can be recovered without training: after semantic clustering, keys and values within each block exhibit strong similarity and can be well summarized by a small set of cluster centroids. Based on this observation, we introduce SVG-EAR, a parameter-free linear compensation branch that uses the centroid to approximate skipped blocks and recover their contributions. While centroid compensation is accurate for most blocks, it can fail on a small subset. Standard sparsification typically selects blocks by attention scores, which indicate where the model places its attention mass, but not where the approximation error would be largest. SVG-EAR therefore performs error-aware routing: a lightweight probe estimates the compensation error for each block, and we compute exactly the blocks with the highest error-to-cost ratio while compensating for skipped blocks. We provide theoretical guarantees that relate attention reconstruction error to clustering quality, and empirically show that SVG-EAR improves the quality-efficiency trade-off and increases throughput at the same generation fidelity on video diffusion tasks. Overall, SVG-EAR establishes a clear Pareto frontier over prior approaches, achieving up to 1.77

\times

and 1.93

\times

speedups while maintaining PSNRs of up to 29.759 and 31.043 on Wan2.2 and HunyuanVideo, respectively.

Xuanyi Zhou, Qiuyang Mang, Shuo Yang +7

UC Berkeley, USA

Video Diffusion Models Efficient Attention Sparse Attention Diffusion Model Inference Acceleration Block-Sparse Attention

Feb 22, 2026cs.LG

Incremental Learning of Sparse Attention Patterns in Transformers

This paper studies simple transformers trained on a high-order Markov chain, where the model must incorporate information from multiple past positions, each with different statistical importance. We show that transformers learn the task incrementally, with each stage corresponding to learning how to copy information from a subset of positions via a sparse attention pattern. Notably, the learning dynamics transition from a competitive phase, where all heads focus on the statistically most important positions, to a cooperative phase, where different heads specialize in different patterns. We model these dynamics with simplified differential equations and prove stage-wise convergence of the resulting system. Functionally, these stages correspond to a sequence of increasingly expressive misspecified models, with the full model class reached only at the end. Overall, we give a theoretical account of how structured attention patterns and head specialization emerge in stages without an explicit curriculum, with implications for generalization in sequential tasks.

Oğuz Kaan Yüksel, Rodrigo Alvarez Lucendo, Nicolas Flammarion

TML Lab, EPFL

Self-Attention Transformer Attention Sparse Attention Incremental Learning Attention Mechanisms Neural Network Training Dynamics+2

Feb 11, 2026cs.LG

Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat

Learned gates can approximate sparse attention patterns on frozen transformers, yet provide limited benefit over random gates when trained jointly with the model. We investigate this difference in a controlled 31M-parameter transformer and attribute it to routing absorption: model representations co-adapt to the imposed mask, reducing the incremental benefit of learned routing. Four experiments characterize the phenomenon. Differentiable soft gating yields perplexities of 48.73 plus or minus 0.60 with learned gates and 49.83 plus or minus 0.04 with frozen random gates over three seeds. Hard top-k masking provides no gradient path to the gate scores in the tested implementation. Gates distilled onto co-adapted and dense-trained Q/K/V both achieve high F1 against oracle masks, but hard-mask deployment yields perplexities of 601.6 and 48.6, respectively. Stochastic mask training also leaves a substantial deployment penalty: dense evaluation yields 78.2 perplexity, compared with 37.3 for the dense baseline. Experiments on Qwen3-1.7B show that increasing the number of trainable attention layers reduces the gap between learned and random gates. We relate these results to co-adaptation in Mixture-of-Experts and propose parameter asymmetry between the gate and the model as a contributing mechanism. For the tested per-query, token-level gates, freezing the model provides stable routing targets and enables effective post-hoc sparsification. The results motivate random-routing controls and separate evaluation of routing quality and model adaptation in sparse attention methods.

Keston Aquino-Michaels

No Way Labs

Transformer Self-Attention Gated Attention Sparse Attention Attention Mechanisms

Feb 9, 2026cs.LG

Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference

A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-oracle top-k KV selection can preserve the quality of dense attention while sharply reducing computation and bandwidth, existing sparse methods generally rely on posterior heuristics, i.e., selectors conditioned on observed attention or proxy scores. Such conditioning introduces posterior bias: it tends to distort true token importance and miss salient tokens, thereby impairing long-range reasoning. To tackle this problem, we propose Pre-hoc Sparsity (PrHS), which selects KV entries before attention scoring and provides explicit accuracy control. Let the attention mass of discarded entries be delta (the dropped mass). Through a marginal-to-mutual-information analysis, we derive an upper bound on the mutual-information loss that depends only on the dropped mass. This relation explains failure modes of posterior heuristics and enables verifiable guarantees by controlling the dropped mass in advance. Within PrHS, we instantiate three orthogonal pre-hoc selectors along the axes of time, depth, and layer. Extensive experiments on LLaMA and Mistral families validate PrHS. Across GSM8K and CoQA, PrHS reduces retrieval overhead by over 90%, achieving 3x higher retrieval sparsity than HShare at matched or better accuracy. It incurs under 1% average degradation on LongBench, lowers attention FLOPs by about 15% versus prior sparse baselines, and yields a 9.9x speedup in attention-operator latency and 2.8x higher throughput on NVIDIA A100-80GB GPUs than the dense baseline.

Yifei Gao, Lei Wang, Rong-Cheng Tu +3

University College London, London, UK · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CAS), Shenzhen 518055, China · The Chinese University of Hong Kong +1

Self-Attention KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration Sparse Attention+1

Feb 6, 2026cs.LG

Attention-Mass Condensation for Sparse Decoding

Attention-mass concentration creates an opportunity for sparse decoding, but retained mass alone does not guarantee a stable greedy decision: retrieval error, omitted value directions, and recursive decoding all matter. We formalize this distinction with an exact omitted-mass identity and a sufficient downstream margin condition, then characterize a query-dependent mean-pooled block selector. On Qwen2-0.5B, a paired fresh-selection sweep covers supports of 97--769 positions, contexts of 2K--16K, and five prefixes per context. The primary exact-match result is that none of 60 runs remains identical to dense decoding through 128 tokens. Distributional quality is distinct: for supports of at least 193, seven of nine context-support conditions have median teacher-forced continuation perplexity changes within 5% of dense, but prompt-level ranges include severe 16K outliers. All seven runs with teacher-forced match below 70% have perplexity increases above 100%; these observations come from two prefixes and suggest a warning regime, not a general threshold. The measured perplexity is teacher-forced on the dense model's own continuation, not the sparse model's free-running output. Separate retrieval and attention-mass probes illustrate why captured mass alone is not a retrieval or decision guarantee. Isolated operator timings do not establish matched-quality acceleration or end-to-end serving speed.

Jorge L. Ruiz Williams

NaNZeta LLC

Language Model Decoding Sparse Attention Autoregressive Decoding Block-Sparse Attention

Jan 17, 2026cs.LG

Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling

Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass disperses as sequence lengths increase. We tackle these problems with Threshold Differential Attention (TDA), a sink-free attention mechanism that achieves ultra-sparsity and improved robustness at longer sequence lengths without the computational overhead of projection methods or the performance degradation caused by noise accumulation of standard rectified attention. TDA applies row-wise extreme-value thresholding with a length-dependent gate, retaining only exceedances. Inspired by the differential transformer, TDA also subtracts an inhibitory view to enhance expressivity. Theoretically, we prove that TDA controls the expected number of spurious survivors per row to

O(1)

and that consensus spurious matches across independent views vanish as context grows. Empirically, TDA produces

>99\%

exact zeros and eliminates attention sinks while maintaining competitive performance on standard and long-context benchmarks.

Xingyue Huang, Xueying Ding, Mingxuan Ju +3

University of Oxford · Carnegie Mellon University · Snap Inc.

Self-Attention Long-Context Language Modeling Sparse Attention Attention Sinks Attention Mechanisms

Jan 14, 2026cs.CV

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a \underline{\textbf{M}}ixture-\underline{\textbf{O}}f-\underline{\textbf{D}}istribution \textbf{DiT} (\textbf{MOD-DiT}), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a {distributed mixing approach} to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches.

Yuxi Liu, Yipeng Hu, Zekun Zhang +2

Peking University · University of Electronic Science and Technology of China · University of Science and Technology of China

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration