Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation

• URL: http://arxiv.org/abs/2601.13683v1
• Date: Tue, 20 Jan 2026 07:33:16 GMT
• Title: Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation
• Abstract summary: Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation.<n>DyDiLA is a novel linear attention formulation that enhances the effectiveness of LiTs by mitigating the oversmoothing issue and improving generation quality.<n>To capitalize on DyDiLA, we introduce a refined LiT, termed DyDi-LiT, that systematically incorporates our advancements.
• Score: 25.321469825055733
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation, yet the quadratic cost of self-attention poses a major scalability bottleneck. To address this, linear attention mechanisms have been adopted to reduce computational cost; unfortunately, the resulting linear diffusion transformers (LiTs) models often come at the expense of generative performance, frequently producing over-smoothed attention weights that limit expressiveness. In this work, we introduce Dynamic Differential Linear Attention (DyDiLA), a novel linear attention formulation that enhances the effectiveness of LiTs by mitigating the oversmoothing issue and improving generation quality. Specifically, the novelty of DyDiLA lies in three key designs: (i) dynamic projection module, which facilitates the decoupling of token representations by learning with dynamically assigned knowledge; (ii) dynamic measure kernel, which provides a better similarity measurement to capture fine-grained semantic distinctions between tokens by dynamically assigning kernel functions for token processing; and (iii) token differential operator, which enables more robust query-to-key retrieval by calculating the differences between the tokens and their corresponding information redundancy produced by dynamic measure kernel. To capitalize on DyDiLA, we introduce a refined LiT, termed DyDi-LiT, that systematically incorporates our advancements. Extensive experiments show that DyDi-LiT consistently outperforms current state-of-the-art (SOTA) models across multiple metrics, underscoring its strong practical potential.

Related papers

• Exact Linear Attention [0.0]
  Exact Linear Attention (ELA) achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions.<n>ELA achieves up to 6x faster decoding speed and 75% reduction in KV cache memory usage compared to full attention.<n>We extend the linear attention principle to vision models, yielding YOLO-LAT, which attains up to 4.3x GPU inference speedup and 7.9x parameter reduction with competitive detection accuracy.
  arXiv  Detail & Related papers  (2026-05-13T08:06:48Z)
• PRISM: Parallel Residual Iterative Sequence Model [52.26239951489612]
  We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension.<n>PRISM introduces a solver-inspired inductive bias that captures key structural properties of multi-step refinement in a parallelizable form.<n>We prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update manifold beyond the single-step Rank-$1$ bottleneck.
  arXiv  Detail & Related papers  (2026-02-11T12:39:41Z)
• Time-Delayed Transformers for Data-Driven Modeling of Low-Dimensional Dynamics [0.0]
  We present a time-delayed transformer (TD-TF) for data-driven modeling of unsteady-temporal dynamics.<n>The architecture is deliberately minimal, consisting of one self-attention layer with a single query per generalization and one feedforward layer.<n> Numerical experiments demonstrate that TD-TF matches the performance of strong linear baselines on near-linear systems, while significantly outperforming them in nonlinear and chaotic regimes.
  arXiv  Detail & Related papers  (2026-02-09T10:22:43Z)
• LINA: Linear Autoregressive Image Generative Models with Continuous Tokens [56.80443965097921]
  Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis.<n>We study how to design compute-efficient linear attention within this framework.<n>We present LINA, a simple and compute-efficient T2I model built entirely on linear attention, capable of generating high-fidelity 1024x1024 images from user instructions.
  arXiv  Detail & Related papers  (2026-01-30T06:44:33Z)
• Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning [30.781578037476347]
  We introduce a novel approach to modeling transformer architectures using highly flexible non-autonomous neural ordinary differential equations (ODEs)<n>Our proposed model parameterizes all weights of attention and feed-forward blocks through neural networks, expressing these weights as functions of a continuous layer index.<n>Our neural ODE transformer demonstrates performance comparable to or better than vanilla transformers across various configurations and datasets.
  arXiv  Detail & Related papers  (2025-03-03T09:12:14Z)
• ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation [83.62931466231898]
  This paper presents ARLON, a framework that boosts diffusion Transformers with autoregressive models for long video generation.<n>A latent Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input latent space of the DiT model into compact visual tokens.<n>An adaptive norm-based semantic injection module integrates the coarse discrete visual units from the AR model into the DiT model.
  arXiv  Detail & Related papers  (2024-10-27T16:28:28Z)
• Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators [83.48423407316713]
  We present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately. Our model initiates the denoising process with a precise, non-ambiguous stage and gradually transitions to a phase enriched with detail. Our method achieves a state-of-the-art FID score of 2.01 when integrated with the recent work SiT.
  arXiv  Detail & Related papers  (2024-08-11T07:01:39Z)
• Dynamical Mean-Field Theory of Self-Attention Neural Networks [0.0]
  Transformer-based models have demonstrated exceptional performance across diverse domains. Little is known about how they operate or what are their expected dynamics. We use methods for the study of asymmetric Hopfield networks in nonequilibrium regimes.
  arXiv  Detail & Related papers  (2024-06-11T13:29:34Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)
• Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization [76.68866368409216]
  We propose learning to dynamically select discretization tightness conditioned on inputs. We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:54:26Z)
• Contrastively Disentangled Sequential Variational Autoencoder [20.75922928324671]
  We propose a novel sequence representation learning method, named Contrastively Disentangled Sequential Variational Autoencoder (C-DSVAE) We use a novel evidence lower bound which maximizes the mutual information between the input and the latent factors, while penalizes the mutual information between the static and dynamic factors. Our experiments show that C-DSVAE significantly outperforms the previous state-of-the-art methods on multiple metrics.
  arXiv  Detail & Related papers  (2021-10-22T23:00:32Z)
• Adaptive Multi-Resolution Attention with Linear Complexity [18.64163036371161]
  We propose a novel structure named Adaptive Multi-Resolution Attention (AdaMRA) for short. We leverage a multi-resolution multi-head attention mechanism, enabling attention heads to capture long-range contextual information in a coarse-to-fine fashion. To facilitate AdaMRA utilization by the scientific community, the code implementation will be made publicly available.
  arXiv  Detail & Related papers  (2021-08-10T23:17:16Z)

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.