Diffusion Model Inference Acceleration

Follow this topic Ask about this topic

Momentum

40 papers in the last four weeks, up 100% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 335

May 15, 2026cs.CV

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to key-value caching, which limits its scalability to long video horizons. Existing remedies (e.g., sparse attention and KV-cache compression) reduce per-step cost but still rely on a linearly growing cache or irreversibly discard past context, and thus fail to address linear memory growth and streaming context management. To address this scalability bottleneck, we propose ARL2 (Attend Locally, Remember Linearly), a hybrid attention module that replaces quadratic cross-frame attention with a fixed-size recurrent state. We decompose self-attention into two branches: an intra-frame softmax branch for spatial detail and local dependencies, and an inter-frame gated recurrent linear branch that maintains a fixed-size state for streaming context. Our key insight is that softmax attention captures fine-grained local interactions, while a recurrent state provides controllable long-range memory. This design achieves linear-time scaling with constant memory while improving temporal consistency over the full-softmax model. To prevent noisy intermediate states from corrupting memory, we update the recurrent state only after the denoised pass. To avoid within-frame information asymmetry, all tokens share the same pre-update state rather than sequential updates. To the best of our knowledge, this is the first work to convert a pretrained AR video diffusion model into a hybrid linear attention architecture, through an efficient two-stage training scheme for AR video. With 75% of layers replaced by hybrid linear attention, the model achieves up to 2.26 wall-clock speedup and 54% memory reduction, while maintaining comparable quality with improving temporal consistency.

Kunyang Li, Mubarak Shah, Yuzhang Shang

Institute of Artificial Intelligence, University of Central Florida

Memory-Augmented Neural Networks Video Diffusion Models Self-Attention Linear Attention Autoregressive Video Generation Diffusion Model Inference Acceleration+1

May 15, 2026cs.LG

Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers

For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schrödinger bridges define probability paths, yet their inference grids are usually heuristic or inherited from one-endpoint diffusion. We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution, and use it to build a training-free entropic inference-time scheduler from first principles. For Gaussian Brownian bridges this rate is closed-form and U-shaped, motivating boundary-heavy nonuniform grids. On trained two-dimensional bridge/flow models, the estimated profile recovers the predicted shape and improves 10-step ODE-Heun MMD over linear by 18.1%, with a paired 22.7% SDE-Heun improvement in the same low-NFE sweep. On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 \pm 4.0 versus 200.5 \pm 2.9 for linear and 238.0 \pm 5.3 for cosine). On AlphaFlow protein generation, entropic conditional-marginal (cond-marg) scheduling shows advantage in low-NFE regimes on both CAMEO22 and ATLAS benchmarks. These results support entropy-rate scheduling as a practical low-budget allocation signal for high-dimensional bridge and flow samplers.

Bruno Trentini, Dejan Stancevic, Michael M. Bronstein +2

NVIDIA Corporation, Santa Clara, CA, USA · University of Oxford, Dept. of Computer Science, Oxford, UK · Donders Institute for Brain, Cognition, and Behaviour, Radboud University, Nijmegen, NL +1

Flow Matching Schrödinger Bridges Few-Step Diffusion Sampling Adaptive Sampling Flow-Based Generative Modeling Diffusion Model Inference Acceleration

May 15, 2026cs.CV

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices entails prohibitive computational and memory overhead. While efficiency-driven approaches like Linear-DiT and static pruning alleviate bottlenecks, they often incur quality degradation. Unlike cloud environments, mobile constraints require a single-model paradigm that dynamically balances fidelity and latency. We introduce ElasticDiT, which achieves this dynamic trade-off by adjusting spatial compression ratios and DiT block depths. By integrating Shift Sparse Block Attention (SSBA) and a Tiny DWT-Distilled VAE (T-DVAE), ElasticDiT reduces inference latency and memory footprint while maintaining image quality. Experiments confirm that ElasticDiT effectively covers a wide range of fidelity-latency trade-offs within a single set of parameters. By jointly adjusting compression and depth, a single ElasticDiT model can be reconfigured on-the-fly to outperform task-specific baselines. Specifically, our flex lite variant achieves an HPS of 32.87, surpassing the Flux model, while maintaining competitive quality at 84.16 percent average sparsity through SSBA. Furthermore, the plug-and-play T-DVAE provides SD3-level reconstruction with only 1/8x the computational cost of standard VAEs, and Flow-GRPO boosts semantic alignment (GenEval: 66.93 to 73.62). These results demonstrate that ElasticDiT offers a versatile, hardware-adaptive solution that eliminates the need for multiple specialized models, providing a promising path for future high-resolution image generation on mobile devices.

Kunpeng Du, Haizhen Xie, Sen Lu +11

Huawei Technologies

Diffusion Transformer Diffusion-Based Image Generation Sparse Attention Diffusion Model Inference Acceleration On-Device Inference

May 15, 2026cs.CV

Efficient Image Synthesis with Sphere Latent Encoder

Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.

Tung Do, Thuan Hoang Nguyen, Hao Li

Mohamed Bin Zayed University of Artificial Intelligence, UAE

Latent Diffusion Models Few-Step Diffusion Sampling Diffusion-Based Image Generation Diffusion Model Inference Acceleration

May 14, 2026cs.CV

Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning

Despite rapid advancements, current text-to-image (T2I) models predominantly rely on a single-step generation paradigm, which struggles with complex semantics and faces diminishing returns from parameter scaling. While recent multi-step reasoning approaches show promise, they are hindered by ungrounded planning hallucinations lacking verification, monolithic post-hoc reflection, long-context optimization instabilities, and prohibitive inference latency. To overcome these bottlenecks, we propose the Closed-Loop Visual Reasoning (CLVR) framework, a comprehensive system that deeply couples visual-language logical planning with pixel-level diffusion generation. CLVR introduces an automated data engine with step-level visual verification to synthesize reliable reasoning trajectories, and proposes Proxy Prompt Reinforcement Learning (PPRL) to resolve long-context optimization instabilities by distilling interleaved multimodal histories into explicit reward signals for accurate causal attribution. Furthermore, to mitigate the severe latency bottleneck caused by iterative denoising, we propose

Δ

-Space Weight Merge (DSWM), a theoretically grounded method that fuses alignment weights with off-the-shelf distillation priors, reducing the per-step inference cost to just 4 NFEs without requiring expensive re-distillation. Extensive experiments demonstrate that CLVR outperforms existing open-source baselines across multiple benchmarks and approaches the performance of proprietary commercial models, unlocking general test-time scaling capabilities for complex visual generation.

Hanbo Cheng, Limin Lin, Ruo Zhang +2

University of Science and Technology of China (USTC) · 2Independent Researcher

Image Generation Compositional T2I Generation RL for Image Generation Diffusion Model Inference Acceleration T2I Diffusion Models

May 14, 2026cs.CV

The Velocity Deficit: Initial Energy Injection for Flow Matching

While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the MSE objective systematically underestimates velocity magnitude, causing generated samples to fail to reach the data manifold-a phenomenon we term Integration Lag. To rectify this, we propose Initial Energy Injection, instantiated via two complementary methods: the training-based Magnitude-Aware Flow Matching (MAFM) and the training-free Scale Schedule Corrector (SSC). Both are grounded in our discovery of a crucial asymmetry: velocity contraction causes harmful kinetic stagnation at the trajectory's start, yet acts as a beneficial denoising mechanism at its end. Empirically, SSC yields significant efficiency gains with zero retraining and just one line of code. On ImageNet-1k (256x256), it improves FID by 44.6% (from 13.68 to 7.58) and achieves a 5x speedup, enabling a 50-step generator (FID 7.58) to beat a 250-step baseline (FID 8.65). Furthermore, our methods generalize to Text-to-Image tasks and high-resolution generation, improving FID on MS-COCO by ~22%.

Linze Li, Zong-Wei Hong, Shen Zhang +4

Jiiov Technology, Beijing, China.

Flow Matching Image Generation Flow-Based Generative Modeling Diffusion Model Inference Acceleration

May 14, 2026cs.CV

HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive because it accelerates pretrained models without retraining, yet existing online top-

p

sparse attention still spends non-negligible cost on mask prediction and applies shared thresholds despite strong head-level heterogeneity. We show that these two overlooked factors limit the practical speed-quality trade-off of training-free sparse attention in Video DiTs. To address them, we introduce a head-wise adaptive framework with two plug-in components: Temporal Mask Reuse, which skips unnecessary mask prediction based on query-key drift, and Error-guided Budgeted Calibration, which assigns per-head top-

p

thresholds by minimizing measured model-output error under a global sparsity budget. On Wan2.1-1.3B and Wan2.1-14B, our method consistently improves XAttention and SVG2, achieving up to 1.93 times speedup at 720P while maintaining competitive video quality and similarity metrics.

Xuzhe Zheng, Yuexiao Ma, Jing Xu +3

1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration

May 14, 2026cs.CV

Image Restoration via Diffusion Models with Dynamic Resolution

Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods based on latent DMs seek to alleviate this issue by utilizing the compressed latent space of a variational autoencoder, they require repeated encoder-decoder inference. This introduces significant additional computational burdens, often resulting in runtime performance that is even inferior to that of their pixel-space counterparts. To mitigate the computational inefficiency, this work proposes projecting data into lower-dimensional subspaces using dynamic resolution DMs to accelerate the inference process. We first fine-tune pre-trained DMs for dynamic resolution priors and adapt DPS and DAPS, which are two widely used pixel-space methods for general image restoration tasks, into the proposed framework, yielding methods we refer to as SubDPS and SubDAPS, respectively. Given the favorable inference speed and reconstruction fidelity of SubDAPS, we introduce an enhanced variant termed SubDAPS++ to further boost both reconstruction efficiency and quality. Empirical evaluations across diverse image datasets and various restoration tasks demonstrate that the proposed methods outperform recent DM-based approaches in the majority of experimental scenarios. The code is available at https://github.com/StarNextDay/SubDAPS.git.

Yang Zheng, Wen Li, Zhaoqiang Liu

School of Computer Science and Engineering, University of Electronic Science and Technology of China.

Diffusion Models for Image Restoration Diffusion-Based Inverse Problems Diffusion Posterior Sampling Diffusion Model Inference Acceleration Diffusion Models

May 13, 2026cs.CV

CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across vision tasks. CoReDiT uses a linear-time spatial coherence score to estimate local redundancy in the latent token lattice and skips high coherence (redundant) tokens in self-attention. To maintain a dense representation and avoid visual discontinuities, we reconstruct skipped attention outputs via coherence-guided aggregation of spatially neighboring retained tokens. We further introduce a progressive, block-adaptive pruning schedule that increases pruning gradually and allocates larger budgets to blocks and denoising steps with higher redundancy. Across state-of-the-art diffusion backbones including PixArt-α and MagicDrive-V2, CoReDiT achieves up to 55% self-attention FLOPs reduction and inference speedups of 1.33x on cloud GPUs and 1.72x on mobile NPUs, while maintaining high visual quality. Notably, CoReDiT also increases on-device memory head-room, enabling higher-resolution generation.

Zhuojin Li, Hsin-Pai Cheng, Hong Cai +2

Qualcomm AI Research†

Diffusion Transformer Visual Token Pruning Diffusion Model Inference Acceleration

May 13, 2026cs.LG

Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations

Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, observational data are extremely sparse, which severely limits the applicability of both classical numerical solvers and existing neural approaches. While neural methods have shown promising results under moderately sparse observations, their inference efficiency at high resolutions is limited, and their accuracy degrades substantially in the extremely sparse regime. In this work, we propose the Di-BiLPS, a unified neural framework that effectively handle both forward and inverse PDE problems under extremely sparse observations. Di-BiLPS combines a variational autoencoder to compress high-dimensional inputs into a compact latent space, a latent diffusion module to model uncertainty, and contrastive learning to align representations. Operating entirely in this latent space, the framework achieves efficient inference while retaining flexible input-output mapping. In addition, we introduce a PDE-informed denoising algorithm based on a variance-preserving diffusion process, which further improves inference efficiency. Extensive experiments on multiple PDE benchmarks demonstrate that Di-BiLPS consistently achieves SOTA performance under extremely sparse inputs (as low as 3%), while substantially reducing computational cost. Moreover, Di-BiLPS enables zero-shot super-resolution, as it allows predictions over continuous spatial-temporal domains.

Zhonghao Li, Chaoyu Liu, Qian Zhang

School of Science, Harbin Institute of Technology, Shenzhen, China · Department of Theoretical Physics and Applied Mathematics, University of Cambridge, Cambridge, United Kingdom

Neural PDE Solvers Latent Diffusion Models PDE Solving Diffusion-Based Inverse Problems Diffusion Model Inference Acceleration PDE Inverse Problems

May 13, 2026cs.CV

OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression

Diffusion-based real-world image super-resolution (Real-ISR) has achieved remarkable perceptual quality; however, directly super-resolving images to 4K remains limited by extreme memory consumption. Consequently, prior methods adopt patch-based inference, sacrificing global context and introducing semantic confusion, spatial inconsistency, and severe latency. We propose OP4KSR, a one-step patch-free 4K SR approach built upon the powerful Flux backbone. By leveraging the extreme-compression F16 VAE, OP4KSR makes 4K SR inference tractable under practical GPU budgets, preserving global spatial-semantic coherence while enabling highly efficient inference. However, adapting this one-step architecture intrinsically triggers severe periodic artifacts. We trace this to a RoPE base frequency allocation mismatch and intra-token spatial ambiguity, both exacerbated by the lack of iterative refinement. To suppress these artifacts, we couple RoPE base frequency rescaling (RFR) with an autocorrelation-based periodicity loss (

\mathcal{L}_\text{AP}

). Furthermore, we curate a dedicated training dataset alongside three benchmarks (one synthetic and two real-world) to advance 4K SR research. Extensive experiments demonstrate that OP4KSR achieves competitive perceptual quality with efficient inference, generating a

4096\times4096

output in only 5.75 seconds on a single NVIDIA H20 GPU.

Chengyan Deng, Pengbin Yu, Zhentao Chen +6

School of Automation Engineering, University of Electronic Science and Technology of China · OPPO AI Center, OPPO Inc. · School of Intelligence Science and Technology, Nanjing University

Diffusion Transformer Diffusion Model Inference Acceleration Image Super-Resolution Diffusion Models

May 13, 2026cs.RO

BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning

While autoregressive (AR) Vision-Language-Action (VLA) models have demonstrated formidable reasoning capabilities in robotic tasks, their sequential decoding process often incurs high inference latency and may amplify error accumulation during long-horizon execution. Discrete Diffusion Language Models (dLLMs) provide a promising alternative through parallel token refinement, but their practical deployment in robotics remains limited by repeated denoising function evaluations (NFEs) and the difficulty of directly applying standard KV caching to bidirectional iterative decoding. To bridge these paradigms, we propose BlockVLA, a framework that adapts pretrained AR backbones into an efficient discrete diffusion policy through a block diffusion paradigm. BlockVLA maintains autoregressive dependencies at the block level while enabling parallel denoising within each block, thereby combining global causal coherence with local parallel generation. This design enables prefix KV-cache reuse across completed blocks, reduces the effective cost of iterative denoising, and provides a smoother transition from AR pretraining to diffusion-based policy fine-tuning. We conduct extensive evaluations on the LIBERO and SimplerEnv benchmarks. Experimental results demonstrate that our BlockVLA achieves a 3.3

\times

inference acceleration over standard discrete diffusion baselines. Furthermore, our model exhibits superior training efficiency, with success rates converging substantially faster than baselines, a gain that is particularly pronounced in complex, long-horizon tasks, where BlockVLA achieves significant performance gains in the early stages of training. This work establishes Block Diffusion as a robust bridge between large-scale pretrained AR models and efficient, high-frequency real-time robotic control.

Ruiheng Wang, Shuanghao Bai, Haoran Zhang +2

Xi'an Jiaotong University

Robotic Manipulation Vision-Language-Action Models Diffusion Language Models Diffusion Model Inference Acceleration

May 13, 2026cs.CV

Test-time Sparsity for Extreme Fast Action Diffusion

Action diffusion excels at high-fidelity action generation but incurs heavy computational costs owing to its iterative denoising nature. Despite current technologies showing promise in accelerating diffusion transformers by reusing the cached features, they struggle to adapt to policy dynamics arising from diverse perceptions and multi-round rollout iterations in open environments. We propose test-time sparsity to tackle this challenge, which aims to accelerate action diffusion by dynamically predicting prunable residual computations for each model forward at test time. However, two bottlenecks remain in this paradigm: 1) repetitive conditional encoding and pruning offset most potential speed gains, and 2) the features cached from previous denoising timesteps cannot constrain large pruning errors under aggressive sparsity. To address the first bottleneck, we design a highly parallelized inference pipeline that minimizes the non-decoder delay to milliseconds. Specifically, we first design a lightweight pruner that shares the encoder with the diffusion transformer. Then, we decouple the encoding and pruning from the autoregressive denoising loop by processing all denoising timesteps in parallel, and overlap the pruner with the decoder forward inference through asynchronism. To overcome the second bottleneck, we introduce an omnidirectional reusing strategy, which achieves 95% sparsity by selectively reusing features cached from the current forward, previous denoising timesteps, and earlier rollout iterations. To learn the rollout-level reusing strategies, we sample a few action trajectories to supervise the sparsified diffusion step by step. Extensive experiments demonstrate that our method reduces FLOPs by 92% and accelerates action generation by 5x, achieving lossless performance with an inference frequency of 47.5 Hz. Our code is available at https://github.com/ky-ji/Test-time-Sparsity.

Kangye Ji, Yuan Meng, Jianbo Zhou +3

Tsinghua University · The Chinese University of Hong Kong

Diffusion Transformer Inference-Time Optimization Diffusion Policy Diffusion Model Caching Diffusion Model Inference Acceleration

May 13, 2026cs.CV

DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution

Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-resolution (STVSR) setting remains limited. Existing diffusion-based STVSR approaches suffer from two issues: (1) low inference efficiency and (2) insufficient utilization of spatiotemporal information. These limitations impede deployment. To address these issues, we introduce DiffST, an efficient spatiotemporal-aware video diffusion framework for real-world STVSR. To improve efficiency, we adapt a pre-trained diffusion model for one-step sampling and process the entire video directly rather than operating on individual frames. Furthermore, to enhance spatiotemporal information utilization, we introduce cross-frame context aggregation (CFCA) and video representation guidance (VRG). The CFCA module aggregates information across multiple keyframes to produce intermediate frames. The VRG module extracts video-level global features to guide the diffusion process. Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17

\times

faster than previous diffusion-based STVSR methods. Code is available at: https://github.com/zhengchen1999/DiffST.

Zheng Chen, Ruofan Yang, Jin Han +5

Shanghai Jiao Tong University · Huawei Noah’s Ark Lab · Duke University +1

Video Diffusion Models Video Super-Resolution Diffusion Model Inference Acceleration Image Super-Resolution

May 12, 2026cs.CV

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity

While the overall inference latency of Video Diffusion Transformers (DiTs) can be substantially reduced through model distillation, per-step inference latency remains a critical bottleneck. Existing acceleration paradigms primarily exploit redundancy across the denoising trajectory; however, we identify a limitation where these step-wise strategies encounter diminishing returns in few-step regimes. In such scenarios, the scarcity of temporal states prevents effective feature reuse or predictive modeling, creating a formidable barrier to further acceleration. To overcome this, we propose Frame Interleaved Sparsity DiT (FIS-DiT), a training-free and operator-agnostic framework that shifts the optimization focus from the temporal trajectory to the latent frame dimension. Our approach is motivated by an intrinsic duality within this dimension: the existence of frame-wise sparsity that permits reduced computation, coupled with a structural consistency where each frame position remains equally vital to the global spatiotemporal context. Leveraging this insight, we implement Frame Interleaved Sparsity (FIS) as an execution strategy that manipulates frame subsets across the model hierarchy, refreshing all latent positions without requiring full-scale block computation. Empirical evaluations on Wan 2.2 and HunyuanVideo 1.5 demonstrate that FIS-DiT consistently achieves 2.11--2.41

\times

speedup with negligible degradation across VBench-Q and CLIP metrics, providing a scalable and robust pathway toward real-time high-definition video generation.

Jian Tang, Jiawei Fan, Qingbin Liu +1

Platform and Content Group, Tencent

Video Diffusion Models Diffusion Transformer Few-Step Diffusion Sampling Diffusion Model Inference Acceleration

May 12, 2026cs.CV

Principled Design of Diffusion-based Optimizers for Inverse Problems

Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference times and cumbersome hyperparameter tuning. While pretrained diffusion models can be reused across tasks without retraining, inference-time hyperparameters such as the noise schedule and posterior sampling weights typically require ad-hoc adjustment for each problem setup. We propose principled reparameterizations that induce invariances, allowing the same hyperparameters to be reused across multiple problems without re-tuning. In addition, building on the RED-diff framework, which reformulates posterior sampling as an optimization problem, we further develop the OptDiff pipeline. OptDiff provides a simplified tuning framework that facilitates the integration of convex optimization tools to accelerate inference. Experiments on image reconstruction, deblurring, and super-resolution show substantial speedups and improved image quality.

Julio Oscanoa, Irmak Sivgin, Cagan Alkan +4

Department of Bioengineering · Deparment of Electrical Engineering · Department of Radiology, Stanford University, USA.

Inference-Time Optimization Diffusion-Based Inverse Problems Diffusion Posterior Sampling Diffusion Model Inference Acceleration Inverse Problems Image Inverse Problems

May 11, 2026cs.DC

ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference

Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This assumption breaks down when the per-GPU compute workload is small. Moreover, on PCIe-only nodes, prefetch and inter-GPU collective communications such as all-reduce and all-to-all contend on the shared PCIe path, exposing prefetch latency even when compute would otherwise hide it. We revisit layerwise offloading as a co-scheduling problem between prefetch and communication, guided by a first-order analytical model that predicts when prefetch can be hidden by computation. Building on this model, we design ChunkFlow, a communication-aware, chunk-granular offloading runtime that adaptively yields to collective communication and smoothly trades GPU memory for prefetch volume. On three representative diffusion transformers running on two H100 GPUs over PCIe with Ulysses sequence parallelism, ChunkFlow delivers up to 1.28x step-time speedup over SGLang's existing layerwise offloading, reduces peak GPU memory by up to 49% over the no-offload baseline at near-identical step time once the workload is large enough, and exposes a tunable memory-latency tradeoff that recovers near-zero step-time overhead in the small-workload regime.

Han Meng, Danny Willow Liu, Dong Li

University of California, Merced · University of Chicago · University of California, Merced and Yotta Labs +1

Diffusion Transformer GPU Acceleration Memory-Efficient Inference Distributed Inference Diffusion Model Inference Acceleration

May 11, 2026cs.RO

Muninn: Your Trajectory Diffusion Model But Faster

Diffusion-based trajectory planners can synthesize rich, multimodal robot motions, but their iterative denoising makes online planning and control prohibitively slow. Existing accelerations either modify the sampler or compress the network--sacrificing plan quality or requiring retraining without accounting for downstream control risk. We address the problem of making diffusion-based trajectory planners fast enough for real-time robot use without retraining the model or sacrificing trajectory quality, and in a way that works across diverse state-space diffusion architectures. Our key insight is that diffusion trajectory planners expose two signals we can exploit: a cheap probe of how their internal trajectory representation changes across steps, and analytic coefficients that describe how denoiser errors affect the sampler's state update. By calibrating the first signal against the second on offline runs, we obtain a per-step score that upper-bounds how far the final trajectory can deviate when we reuse a cached denoiser output, and we treat this bound as an uncertainty budget that we can spend over the denoising process. Building on this insight, we present Muninn, a training-free caching wrapper that tracks this uncertainty budget during sampling and, at each diffusion step, chooses between reusing a cached denoiser output when the predicted deviation is small and recomputing the denoiser when it is not. Across standard benchmarks Muninn delivers up to 4.6x wall-clock speedups across several trajectory diffusion models by reducing denoiser evaluations, while preserving task performance and safety metrics. Muninn further certifies that cached rollouts remain within a specified distance of their full-compute counterparts, and we validate these gains in real-time closed-loop navigation and manipulation hardware deployments. Project page: https://github.com/gokulp01/Muninn.

Gokul Puthumanaillam, Hao Jiang, Ruben Hernandez +4

University of Illinois Urbana-Champaign. · Florida International University. · Providence College.

Trajectory Generation Diffusion-Based Planning Diffusion Model Caching Robot Motion Planning Diffusion Model Inference Acceleration

May 10, 2026cs.CV

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video diffusion models still suffer from significant attention complexity and severe memory overhead due to the redundant key-value (KV) caches across historical frames, which limits scalability. In this paper, we tackle this challenge by introducing KV cache compression into autoregressive video diffusion. We observe that attention heads in mainstream AR diffusion models exhibit markedly distinct attention patterns and functional roles that remain stable across samples and denoising steps. Building on our empirical study of head-wise functional specialization, we divide the attention heads into two categories: static heads, which focus on transitions across autoregressive chunks and intra-frame fidelity, and dynamic heads, which govern inter-frame motion and consistency. We then propose Forcing-KV, a hybrid KV cache compression strategy that performs structured static pruning for static heads and dynamic pruning based on segment-wise similarity for dynamic heads. While maintaining output quality, our method achieves a generation speed of over 29 frames per second on a single NVIDIA H200 GPU along with 30% cache memory reduction, delivering up to 1.35x and 1.50x speedups on LongLive and Self Forcing at 480P resolution, and further scaling to 2.82x speedup at 1080P resolution. Code and demo videos are provided at https://zju-jiyicheng.github.io/Forcing-KV-Page.

Yicheng Ji, Zhizhou Zhong, Jun Zhang +7

ZJU · Video Rebirth · HKUST +1

Diffusion Model Caching KV-Cache Compression Autoregressive Video Generation Diffusion Model Inference Acceleration

May 10, 2026cs.CL

Edit-Based Refinement for Parallel Masked Diffusion Language Models

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a mismatch between token-level training objectives and joint sequence consistency. In this paper, we propose ME-DLM, an edit-based refinement framework that augments diffusion generation with lightweight post-editing steps. After producing an initial complete response, the model refines it through minimal edit operations, including replacement, deletion, and insertion, conditioned on the full sequence. Training supervision is derived from edit distance, providing a deterministic signal under a fixed canonicalization scheme for learning minimal corrections. This approach encourages sequence-level consistency through globally conditioned edits while preserving the efficiency benefits of parallel diffusion decoding. Extensive experiments demonstrate that ME-DLM improves the quality and robustness of multi-token parallel generation. In particular, when built upon LLaDA, our method achieves consistent gains of 11.6 points on HumanEval and 33.6 points on GSM8K while using one-eighth of the total diffusion steps. Code is available at https://github.com/renhouxing/ME-DLM.

Houxing Ren, Mingjie Zhan, Zimu Lu +5

CUHK MMLab · SenseTime Research · Shenzhen Loop Area Institute +1

Masked Diffusion Models Parallel Decoding Diffusion Language Model Decoding Diffusion Language Models Diffusion Model Inference Acceleration Text Generation

May 10, 2026cs.CV

When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation

Identity-preserved image generation is typically built on many-step diffusion backbones, making personalized generation expensive at deployment time. We show that this cost is often unnecessary for identity-conditioned FLUX generation. A frozen InfuseNet identity adapter trained with dev transfers directly to the distilled schnell backbone without retraining. This two-line replacement -- changing the backbone path and disabling classifier-free guidance -- reduces latency by 5.9x while improving ArcFace identity similarity by +0.028 and lpips by -0.016 over the standard 28-step dev baseline. To explain why this works, we analyze the denoising trajectory and find that identity fidelity enters an early effective regime, often within 4-8 steps, while later steps primarily refine visual detail, sharpness, and contrast. Adapter ablations confirm that identity formation depends on the identity adapter, while attention-stream norm probes suggest that the relative conditioning contribution decreases as sampling proceeds. Preliminary style-adapter and object-adapter sweeps on SDXL and SD1.5 show similar diminishing returns after intermediate steps. These results position distilled backbone replacement as a simple, training-free strategy for improving the efficiency-fidelity tradeoff of identity-preserved generation.

Dongqi Zheng

Identity-Preserving Image Generation Few-Step Diffusion Sampling Diffusion Model Acceleration Diffusion Model Inference Acceleration

May 10, 2026cs.CV

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation

Streaming long-video generation faces a central challenge in continuous semantic switching, requiring adaptive memory to preserve coherent visual evolution. Current approaches rely on cache rebuilding at prompt boundaries or fixed memory budgets, but they introduce redundant computation and limit flexible semantic adaptation. This limitation arises from a mismatch between cached video history and prompt updates, as memory preserves visual continuity while prompt switches demand rapid semantic adaptation. Motivated by this observation, we present SWIFT, Semantic Windowing and Injection for Flexible Transitions, a training-free framework for multi-prompt long-video generation that enables efficient semantic switching while preserving temporal coherence in causal video diffusion models. SWIFT introduces a lightweight Semantic Injection Cache that augments cached video memory rather than reconstructing it from scratch at every prompt boundary. To avoid uniformly perturbing all attention channels, we further perform head-wise semantic injection, so that each attention head receives a prompt update proportional to its alignment with the current video state. In addition, we introduce an Adaptive Dynamic Window that allocates temporal memory according to prompt phase, using larger local context near switching boundaries and smaller windows during stable segments to reduce average inference cost. To preserve long-range semantic consistency under compressed local attention, we further maintain segment-level semantic anchors that summarize prompt-conditioned video history and reintroduce it as compact memory tokens. Compared with current state-of-the-art methods, SWIFT preserves generation quality while achieving 22.6 FPS on a single H100 GPU, establishing a substantially more efficient solution for multi-prompt long-video generation. Our code is available at https://github.com/ShanwenTan/SWIFT.

Shanwen Tan, Hao Li, Jingtao Zhang +4

University of Science and Technology of China · Fudan University · Georgia Institute of Technology +1

Long Video Generation Memory-Augmented Video Generation Streaming Video Generation Video Generation Diffusion Model Caching Diffusion Model Inference Acceleration+1

May 9, 2026cs.AI

Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation

Reasoning-based end-to-end (E2E) autonomous driving has recently emerged as a promising approach to improving the interpretability of driving decisions as it can generate human-readable reasoning together with predicted trajectories. Such approaches commonly generate multiple trajectories to capture diverse future behaviors, and they fall into two categories: (1) multi-reasoning, where one reasoning sequence is generated per trajectory, and (2) single-reasoning, where a single reasoning is shared across all trajectories. The former offers richer diversity at the cost of redundant computation, while the latter is more efficient but is often assumed to sacrifice diversity. Alpamayo 1, a representative system, adopts the multi-reasoning approach and achieves competitive trajectory prediction performance. However, the efficiency of this design remains largely unexplored, making it a well-motivated subject for investigation. In this paper, we systematically analyze and improve Alpamayo 1 in two ways. First, we reduce inference latency while preserving trajectory diversity by redesigning Alpamayo 1 into a single-reasoning system. Through extensive experiments, we find that replacing multi-reasoning with single-reasoning does not meaningfully degrade trajectory diversity. Second, we accelerate diffusion-based action generation by eliminating inter-block overhead arising from unnecessary copy operations and inefficient kernel execution. Through closed-loop and open-loop experiments, we validate both optimizations, demonstrating a 69.23% reduction in inference latency while maintaining trajectory diversity and prediction quality. These results highlight the importance of jointly analyzing system architecture and runtime execution to improve the efficiency of reasoning-based E2E AD systems.

Yunseong Jeon, Namcheol Lee, Yoonsu Lee +4

Graduate School of Automobile and Mobility, Kookmin University, Seoul, Republic of Korea · Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea

Efficient Inference End-to-End Autonomous Driving Diffusion-Based Planning Vehicle Trajectory Prediction Diffusion Model Inference Acceleration

May 9, 2026cs.AI

SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference

The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency. However, existing continuous batching methods suffer from severe resource contention during UNet-VAE concurrency, leading to latency spikes. Furthermore, concurrent multi-task scheduling entails a trade-off between UNet throughput and VAE latency across varying scheduling strategies. To address these, we propose SynerDiff, an efficient continuous batching system built on intra-inter level synergy. At the intra-concurrency level, SynerDiff alleviates resource contention by pruning component-specific resource bottlenecks via VAE Chunking and Adaptive Skip-CFG. At the inter-concurrency level, leveraging components' differential sensitivity to scheduling granularities, a threshold-aware scheduler plans concurrent sequences and tunes intra-concurrency decisions to minimize VAE latency while maintaining UNet within high-throughput threshold. Additionally, a feedback controller dynamically adjusts this threshold based on queue loads to boost system capacity ceiling. Experimental results show that, SynerDiff improves throughput by 1.6

\times

and decreases both average E2E and P99 tail latencies by up to 78.7%, compared to benchmarks while guaranteeing high image fidelity.

Ziqi Zhou, Peng Yang, Yuxin Liang +2

School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China · The State Grid Hubei Electric Power Research Institute, Wuhan, China · Jincheng Yunxiang Big Data Technology Operation Co., Ltd., Shanxi, China

Diffusion Model Serving Diffusion Model Inference Acceleration Diffusion Models

May 9, 2026cs.RO

ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation

Diffusion policies have demonstrated exceptional performance in embodied AI. However, their iterative denoising process results in high latency, and existing acceleration methods often sacrifice physical consistency. To address this, we propose ElasticFlow, a distillation-free, physics-consistent one-step policy framework. We reconstruct the Mean Field Theory by directly modeling the average velocity field, enabling a direct single-step mapping from noise to action. Addressing the Temporal Heterogeneity of robotic tasks, we introduce the Elastic Time Horizons mechanism. This mechanism effectively overcomes Spectral Bias by explicitly encoding control granularity, achieving efficient alignment between semantic instructions and physical execution horizons. Experiments on benchmarks such as LIBERO, CALVIN, and RoboTwin demonstrate that ElasticFlow achieves efficient 1-NFE inference (approximately 71Hz). Furthermore, it outperforms state-of-the-art methods, including OpenVLA and

π_0

, on long-horizon tasks, highlighting its potential for efficient, robust, and semantically aligned control.

Kewei Chen, Yayu Long, Shuai Li +1

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences · Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland

Flow Matching Long-Horizon Robotic Manipulation Language-Conditioned Robot Manipulation Diffusion Policy Diffusion Model Inference Acceleration

May 9, 2026cs.LG

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence levels, which ensures negligible discrepancy between the marginal and joint distributions. However, the stringent confidence thresholds required to preserve accuracy severely constrain the scalability of parallelism. Through systematic token-level statistical analysis, we reveal that a substantial proportion of tokens converge to their correct predictions early in the denoising process yet fail to reach standard confidence thresholds, confirming that current confidence-based criteria are overly conservative. In response, we introduce LEAP (Lookahead Early-Convergence Token Detection for Accelerated Parallel Decoding). LEAP is a training-free, plug-and-play method that leverages future context filtering and multi-sequence superposition to detect early-converging tokens. By validating the alignment between early convergence and correctness, we enable reliable early decoding of these tokens. Benchmarking across diverse domains demonstrates that LEAP significantly lowers inference latency and decoding steps. Compared to confidence-based decoding, the average number of denoising steps is reduced by about 30%. On the GSM8K dataset, combining LEAP with dParallel accelerates decoding to 7.2 tokens per step while preserving model precision. LEAP effectively breaks the reliance on high-confidence priors, offering a novel paradigm for parallel decoding.

Haohui Zhang, Zhiye Wang, Xiaoying Gan +2

Shanghai Jiao Tong University

Parallel Decoding Diffusion Language Model Decoding Diffusion Model Inference Acceleration

May 9, 2026cs.CV

ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction

Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch. We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.

Alen Mrdovic, Qingze, Liu +6

Tony · Rutgers University, New Brunswick · The College of New Jersey

Trajectory Generation Multi-Agent Trajectory Prediction Consistency Distillation Agent Trajectory Analysis Conditional Generative Modeling Diffusion Model Inference Acceleration+1

May 8, 2026cs.CV

PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction

Positron Emission Tomography (PET) image reconstruction is inherently challenged by Poisson noise and physical degradation factors, which are further exacerbated in limited-angle acquisitions. While deep learning methods demonstrate promising performance, their generalization to unseen clinical data distributions remains limited without extensive retraining. We propose PET-Adapter, a test-time domain adaptation framework for generative PET reconstruction models pretrained solely on phantom data. Our method enables adaptation to clinical datasets with varying anatomies, tracers, and scanner configurations without requiring paired ground truth. PET-Adapter introduces layer-wise low-rank anatomical conditioning during adaptation and Ordered Subset Expectation Maximization-based warm-starting that initializes the generation from physics-informed reconstructions, reducing diffusion steps from 50 to 2 without compromising quality. Experiments across multiple clinical datasets demonstrate superior 3D reconstruction performance in both full-angle and limited-angle settings, highlighting the clinical feasibility and computational efficiency of the proposed approach.

Rüveyda Yilmaz, Yuli Wu, Johannes Stegmaier +1

Institute of Imaging and Computer Vision, RWTH Aachen University, Germany · Machine Learning for Medical Data, Heinrich Heine University Düsseldorf, Germany

Test-Time Adaptation Image Reconstruction PET/CT Imaging Diffusion Model Inference Acceleration

May 8, 2026cs.LG

Stochastic Transition-Map Distillation for Fast Probabilistic Inference

Diffusion models achieve strong generation quality, diversity, and distribution coverage, but their performance often comes with expensive inference. In this work, we propose Stochastic Transition-Map Distillation (STMD), a teacher-free framework for accelerating diffusion model inference while preserving probabilistic sample generation. In contrast to score-based diffusion models, whose denoising parametrization models the mean of the posterior distribution, STMD distills the full transition map associated with the sampling stochastic differential equation (SDE). We parameterize these SDE transitions with a conditional Mean Flow model, yielding a one- or few-step stochastic sampler that retains the transition structure of the underlying diffusion process. This perspective is especially useful for downstream tasks that require stochastic inference, such as diffusion posterior sampling, inverse problems, and energy-based fine-tuning. Compared to recent distillation methods, STMD requires no pretrained teacher, bi-level optimization, or trajectory simulation and caching, enabling efficient and scalable training. We derive convergence bounds for our method in the Wasserstein distance, providing a strong theoretical foundation for our approach, and validate STMD on various image generation examples on the MNIST, CIFAR-10, and CelebA datasets.

George Rapakoulias, Peter Garud, Lingjiong Zhu +1

Department of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA · Department of Mathematics, Florida State University, Tallahassee, FL

Diffusion Model Distillation MeanFlow Diffusion Sampling Few-Step Diffusion Sampling Diffusion Model Inference Acceleration

May 8, 2026cs.CV

LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling

Distilled diffusion models accelerate image generation by reducing the number of denoising steps, but often suffer from degraded image quality. To mitigate this trade-off, test-time optimization methods improve quality, yet their iterative nature incurs substantial computational overhead and leads to slow inference, limiting practical usability. Recent hypernetwork-based approaches amortize this process during training, but still require costly noise modulation in high-dimensional latent spaces. In this work, we propose LENS (Low-frequency Eigen Noise Shaping), an efficient noise modulation framework that operates in a low-dimensional subspace. Our approach is motivated by the observation that low-frequency components of the noise largely determine the global structure and visual fidelity of generated images. Based on this observation, we provide a theoretical justification for restricting modulation to the low-frequency subspace and derive a principled training objective. Building on this, LENS employs a lightweight, standalone network to selectively modulate these components, enabling efficient and targeted noise modulation. Extensive experiments demonstrate that LENS achieves competitive image quality while reducing FLOPs by 400-700

\times

, model parameters by 25-75

\times

, and inference-time overhead by 10-20

\times

compared to prior methods.

Haewon Jeon, Si-Hyeon Lee

School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon, South Korea

Diffusion Model Distillation Few-Step Diffusion Sampling Diffusion Model Inference Acceleration Diffusion Models