LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models

• URL: http://arxiv.org/abs/2603.13450v1
• Date: Fri, 13 Mar 2026 15:12:41 GMT
• Title: LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models
• Abstract summary: Locality-Aware Dynamic Rescue (LADR) is a training-free method that expedites inference by exploiting the spatial Markov property of images.<n>LADR prioritizes the recovery of tokens at the ''generation frontier'', regions spatially adjacent to observed pixels.<n>Experiments on four text-to-image generation benchmarks demonstrate that our LADR achieves an approximate 4 x speedup over standard baselines.
• Score: 10.535207607235046
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Discrete Diffusion Language Models have emerged as a compelling paradigm for unified multimodal generation, yet their deployment is hindered by high inference latency arising from iterative decoding. Existing acceleration strategies often require expensive re-training or fail to leverage the 2D spatial redundancy inherent in visual data. To address this, we propose Locality-Aware Dynamic Rescue (LADR), a training-free method that expedites inference by exploiting the spatial Markov property of images. LADR prioritizes the recovery of tokens at the ''generation frontier'', regions spatially adjacent to observed pixels, thereby maximizing information gain. Specifically, our method integrates morphological neighbor identification to locate candidate tokens, employs a risk-bounded filtering mechanism to prevent error propagation, and utilizes manifold-consistent inverse scheduling to align the diffusion trajectory with the accelerated mask density. Extensive experiments on four text-to-image generation benchmarks demonstrate that our LADR achieves an approximate 4 x speedup over standard baselines. Remarkably, it maintains or even enhances generative fidelity, particularly in spatial reasoning tasks, offering a state-of-the-art trade-off between efficiency and quality.

Related papers

• Isotropic Embedding Perturbations for Robust Vision Language Encoders [73.92626712781859]
  Aether is a simple plug-in method that applies diffusion-style random perturbations in the embedding space via controlled alpha-mixing.<n>Inspired by feature-space perturbations in language models and image degradation in generative pretraining, Aether induces mild yet effective perturbations.<n>Aether delivers consistent gains over the advanced recipe combining CutMix, Mixup, DropPath, and RandAug.
  arXiv  Detail & Related papers  (2026-09-09T15:08:05Z)
• Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation [44.1310706833305]
  DDB is a framework designed to resolve the fundamental misalignment of standard discrete diffusion in image translation and generation.<n>We introduce a hybrid absorption mechanism that absorbs the state to a mixture of mask and source tokens, effectively injecting source prior as spatial anchors into the latent space.<n>Experiments validate the versatility and robustness of our framework across diverse generative paradigms.
  arXiv  Detail & Related papers  (2026-08-30T19:44:38Z)
• Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution [80.28905986756685]
  DiMOO-SR is a rarity-aware multimodal discrete diffusion framework for photo-realistic image Super-Resolution.<n>Experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps.
  arXiv  Detail & Related papers  (2026-07-20T07:01:01Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration [47.52310736101766]
  Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches.<n>We address this via a cloud-device collaboration framework textbfCIAR, which utilizes on-device self-verification to handle two key properties of visual synthesis.<n>Our solution centers on an on-device token uncertainty quantifier, which adopts continuous probability intervals to accelerate processing and make it feasible for large visual vocabularies.
  arXiv  Detail & Related papers  (2026-03-26T14:04:50Z)
• Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents [10.559617160878227]
  GUIPruner is a training-free framework tailored for high-resolution GUI navigation.<n>It synergizes Temporal-temporal Resolution (TAR) and Stratified Structure-aware Pruning (SSP)<n>It consistently achieves state-of-the-art performance, effectively preventing the collapse observed in large-scale models under high-resolution compression.
  arXiv  Detail & Related papers  (2026-02-26T17:12:40Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent Diffusion [11.99197806023714]
  generative image steganography has attracted increasing attention due to its high imperceptibility and flexibility.<n>Existing generative steganography methods often maintain acceptable security and robustness only at relatively low embedding rates.<n>We propose a novel DTAMS framework that achieves high embedding rates while ensuring strong robustness and security.
  arXiv  Detail & Related papers  (2026-02-01T11:15:25Z)
• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding [36.74241893088594]
  Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation.<n>Recent works have accelerated inference via KV cache reuse or decoding, but overlook the intrinsic inefficiencies within the block-wise diffusion process.<n>We propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions.
  arXiv  Detail & Related papers  (2026-01-25T17:36:04Z)
• Multi-Scale Local Speculative Decoding for Image Generation [10.239314110594249]
  We introduce Multi-Scale Local Speculative Decoding (MuLo-SD)<n>MuLo-SD combines multi-resolution drafting with spatially informed verification to accelerate AR image generation.<n>We demonstrate that MuLo-SD achieves substantial speedups up to $mathbf1.7times$.
  arXiv  Detail & Related papers  (2026-01-08T17:39:35Z)
• Training-Free Generation of Diverse and High-Fidelity Images via Prompt Semantic Space Optimization [50.5332987313297]
  We propose Token-Prompt embedding Space Optimization (TPSO), a training-free and model-agnostic module.<n>TPSO introduces learnable parameters to explore underrepresented regions of the token embedding space, reducing the tendency of the model to repeatedly generate samples from strong modes of the learned distribution.<n>In experiments on MS-COCO and three diffusion backbones, TPSO significantly enhances generative diversity, improving baseline performance from 1.10 to 4.18 points, without sacrificing image quality.
  arXiv  Detail & Related papers  (2025-11-25T00:42:09Z)
• EfficientIML: Efficient High-Resolution Image Manipulation Localization [38.432078329653926]
  We propose a novel high-resolution SIF dataset of 1200+ diffusion-generated manipulations with semantically extracted masks.<n>We propose a novel EfficientIML model with a lightweight, three-stage EfficientRWKV backbone.<n>Our approach outperforms ViT-based and other SOTA lightweight baselines in localization performance, FLOPs and inference speed.
  arXiv  Detail & Related papers  (2025-09-10T13:32:02Z)
• Parallel Sequence Modeling via Generalized Spatial Propagation Network [80.66202109995726]
  Generalized Spatial Propagation Network (GSPN) is a new attention mechanism for optimized vision tasks that inherently captures 2D spatial structures.<n>GSPN overcomes limitations by directly operating on spatially coherent image data and forming dense pairwise connections through a line-scan approach.<n>GSPN achieves superior spatial fidelity and state-of-the-art performance in vision tasks, including ImageNet classification, class-guided image generation, and text-to-image generation.
  arXiv  Detail & Related papers  (2025-01-21T18:56:19Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.