Diffusion Transformer

Also known as DiT

Follow this topic Ask about this topic

Diffusion Transformers (DiTs) use transformer networks to turn noise into data, typically by repeatedly predicting denoising updates or following a learned flow. Work explores latent- and pixel-space models, conditioning through text, images, geometry, or other modalities, and representation-learning methods that improve generation and downstream perception. To lower the cost of training and inference, researchers use sparse attention, token reduction, caching, quantization, distillation, and hardware-aware designs. A central challenge is balancing speed, memory, and model size against fidelity, temporal or spatial consistency, and reliable performance across tasks and benchmarks.

Latest papers

473 papers78 papers in the last four weeks, up 100% on the four weeks before. 0.5% of all new papers.

Mar 11, 2026

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers

Diffusion Transformers have established a new state-of-the-art in image synthesis, but the high computational cost of iterative sampling severely hampers their practical deployment. While existing acceleration methods often focus on the temporal domain, they overlook the substantial spatial redundancy inherent in the generative process, where global structures emerge long before fine-grained details are formed. The uniform computational treatment of all spatial regions represents a critical inefficiency. In this paper, we introduce Just-in-Time (JiT), a novel training-free framework that addresses this challenge by acceleration in the spatial domain. JiT formulates a spatially approximated generative ordinary differential equation (ODE) that drives the full latent state evolution based on computations from a dynamically selected, sparse subset of anchor tokens. To ensure seamless transitions as new tokens are incorporated to expand the dimensions of the latent state, we propose a deterministic micro-flow, a simple and effective finite-time ODE that maintains both structural coherence and statistical correctness. Extensive experiments on the state-of-the-art FLUX.1-dev model demonstrate that JiT achieves up to a 7x speedup with nearly lossless performance, significantly outperforming existing acceleration methods and establishing a new and superior trade-off between inference speed and generation fidelity.

Wenhao Sun, Ji Li, Zhaoqiang Liu

University of Electronic Science and Technology of China · Capital Normal University

Diffusion Model Inference Acceleration Diffusion Models Diffusion Transformer

Mar 11, 2026

Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers

Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail. However, existing text-guided diffusion models offer only coarse global control and lack the ability to enforce fine-grained structural constraints. Progress is further limited by the absence of large datasets that pair patch-level spatial layouts with detailed diagnostic descriptions, since generating such annotations for gigapixel whole-slide images is prohibitively time-consuming for human experts. To overcome these challenges, we first develop a scalable multi-agent LVLM annotation framework that integrates image description, diagnostic step extraction, and automatic quality judgment into a coordinated pipeline, and we evaluate the reliability of the system through a human verification process. This framework enables efficient construction of fine-grained and clinically aligned supervision at scale. Building on the curated data, we propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer. Through hierarchical multimodal attention, IC-DiT maintains global semantic coherence while accurately preserving structural and morphological details. Extensive experiments on five histopathology datasets show that IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods. In addition, the generated images serve as effective data augmentation resources for downstream tasks such as cancer classification and survival analysis.

Yuntao Shou, Xiangyong Cao, Qian Zhao +1

Xi’an Jiaotong University

Image Generation Medical Image Synthesis Controllable Image Generation Diffusion Transformer Multimodal Diffusion Models Computational Pathology

Mar 10, 2026

FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of spatio-temporal tokens which can be modeled using Diffusion Transformers (DiTs). However, this approach faces a trade-off between the strong but expensive Full 3D Attention and the efficient but temporally limited Local Factorized Attention. To resolve this trade-off, we propose Matrix Attention, a frame-level temporal attention mechanism that processes an entire frame as a matrix and generates query, key, and value matrices via matrix-native operations. By attending across frames rather than tokens, Matrix Attention effectively preserves global spatio-temporal structure and adapts to significant motion. We build FrameDiT-G, a DiT architecture based on MatrixAttention, and further introduce FrameDiT-H, which integrates Matrix Attention with Local Factorized Attention to capture both large and small motion. Extensive experiments show that FrameDiT-H achieves state-of-the-art results across multiple video generation benchmarks, offering improved temporal coherence and video quality while maintaining efficiency comparable to Local Factorized Attention.

Minh Khoa Le, Kien Do, Duc Thanh Nguyen +1

Applied Artificial Intelligence Initiative, Deakin University, Australia · FPT Smart Cloud, Vietnam · Deakin University, Australia

Efficient Video Generation Video Diffusion Models Video Generation Diffusion Transformer Temporal Attention Temporal Consistency in Video Generation

Mar 10, 2026

When to Lock Attention: Training-Free KV Control in Video Diffusion

Maintaining background consistency while enhancing foreground quality remains a core challenge in video editing. Injecting full-image information often leads to background artifacts, whereas rigid background locking severely constrains the model's capacity for foreground generation. To address this issue, we propose KV-Lock, a training-free framework tailored for DiT-based video diffusion models. Our core insight is that the hallucination metric (variance of denoising prediction) directly quantifies generation diversity, which is inherently linked to the classifier-free guidance (CFG) scale. Building upon this, KV-Lock leverages diffusion hallucination detection to dynamically schedule two key components: the fusion ratio between cached background key-values (KVs) and newly generated KVs, and the CFG scale. When hallucination risk is detected, KV-Lock strengthens background KV locking and simultaneously amplifies conditional guidance for foreground generation, thereby mitigating artifacts and improving generation fidelity. As a training-free, plug-and-play module, KV-Lock can be easily integrated into any pre-trained DiT-based models. Extensive experiments validate that our method outperforms existing approaches in improved foreground quality with high background fidelity across various video editing tasks.

Tianyi Zeng, Jincheng Gao, Tianyi Wang +8

Shanghai Jiao Tong University, Shanghai, China · Tongji University, Shanghai, China · The University of Texas at Austin, Austin, TX, USA +3

Video Diffusion Models Video Editing Attention Control in Diffusion Models Diffusion Model Guidance Diffusion Transformer

Mar 10, 2026

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance efficiency and accuracy. In this paper, with theoretical justification, we indicate that binarization of attention preserves the essential similarity relationships, and propose BinaryAttention, an effective method for fast and accurate 1-bit qk-attention. Specifically, we retain only the sign of queries and keys in computing the attention, and replace the floating dot products with bit-wise operations, significantly reducing the computational cost. We mitigate the inherent information loss under 1-bit quantization by incorporating a learnable bias, and enable end-to-end acceleration. To maintain the accuracy of attention, we adopt quantization-aware training and self-distillation techniques, mitigating quantization errors while ensuring sign-aligned similarity. BinaryAttention is more than 2x faster than FlashAttention2 on A100 GPUs. Extensive experiments on vision transformer and diffusion transformer benchmarks demonstrate that BinaryAttention matches or even exceeds full-precision attention, validating its effectiveness. Our work provides a highly efficient and effective alternative to full-precision attention, pushing the frontier of low-bit vision and diffusion transformers. The codes and models can be found at https://github.com/EdwardChasel/BinaryAttention.

Chaodong Xiao, Zhengqiang Zhang, Lei Zhang

The Hong Kong Polytechnic University · OPPO Research Institute

Attention Quantization Attention Mechanisms Vision Transformer Diffusion Transformer

Mar 10, 2026

RAE-NWM: Navigation World Model in Dense Visual Representation Space

Visual navigation requires agents to reach goals in complex environments through perception and planning. World models address this task by simulating action-conditioned state transitions to predict future observations. Current navigation world models typically learn state evolution under actions within the compressed latent space of a Variational Autoencoder, where spatial compression often discards fine-grained structural information and hinders precise control. To better understand the propagation characteristics of different representations, we conduct a linear dynamics probe and observe that dense DINOv2 features exhibit stronger linear predictability for action-conditioned transitions. Motivated by this observation, we propose the Representation Autoencoder-based Navigation World Model (RAE-NWM), which models navigation dynamics in a dense visual representation space. We employ a Conditional Diffusion Transformer with Decoupled Diffusion Transformer head (CDiT-DH) to model continuous transitions, and introduce a separate time-driven gating module for dynamics conditioning to regulate action injection strength during generation. Extensive evaluations show that modeling sequential rollouts in this space improves structural stability and action accuracy, benefiting downstream planning and navigation.

Mingkun Zhang, Wangtian Shen, Fan Zhang +3

Department of Precision Instrument, Tsinghua University, Beijing, China · University of Rochester, Rochester, NY, USA · Beijing Information Science and Technology University, Beijing, China

Visual Navigation World Model Learning Visual Representation Learning Diffusion Transformer Action-Conditioned World Models

Mar 9, 2026

TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers

Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by sharpening attention distributions, but fail to preserve fine-grained semantic details and introduce obvious artifacts. In this work, we analyze the characteristics of DiTs and propose TIDE, a training-free text-to-image (T2I) extrapolation method that enables generation with arbitrary resolution and aspect ratio without additional sampling overhead. We identify the core factor for prompt information loss, and introduce a text anchoring mechanism to correct the imbalance between text and image tokens. To further eliminate artifacts, we design a dynamic temperature control mechanism that leverages the pattern of spectral progression in the diffusion process. Extensive evaluations demonstrate that TIDE delivers high-quality resolution extrapolation capability and integrates seamlessly with existing state-of-the-art methods.

Yihua Liu, Fanjiang Ye, Bowen Lin +2

Independent Researcher · Rice University · University of Houston

T2I Diffusion Models Diffusion Transformer T2I Generation Attention Control in Diffusion Models

Mar 8, 2026

Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion Transformers

In this study, we present a conditional diffusion-transformer framework for generating ensembles of three-dimensional Escherichia coli genome conformations guided by Hi-C contact maps. Instead of producing a single deterministic structure, we formulate genome reconstruction as a conditional generative modeling problem that samples heterogeneous conformations whose ensemble-averaged contacts are consistent with the input Hi-C data. A synthetic dataset is constructed using coarse-grained molecular dynamics simulations to generate chromatin ensembles and corresponding Hi-C maps under circular topology. Our models operate in a latent diffusion setting with a variational autoencoder that preserves per-bin alignment and supports replication-aware representations. Hi-C information is injected through a transformer-based encoder and cross-attention, enforcing a physically interpretable one-way constraint from Hi-C to structure. The model is trained using a flow-matching objective for stable optimization. On held-out ensembles, generated structures reproduce the input Hi-C distance-decay and structural correlation metrics while maintaining substantial conformational diversity, demonstrating the effectiveness of diffusion-based generative modeling for ensemble-level 3D genome reconstruction.

Mingxin Zhang, Xiaofeng Dai, Yu Yao +1

The University of Tokyo · The University of Michigan · Waseda University

Genomics Conditional Diffusion Models Diffusion Transformer

Mar 7, 2026

SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer

Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offers high acceleration efficiency but often compromises fidelity, whereas pruning shows the opposite trade-off. Integrating caching with pruning achieves a balance between acceleration and generation quality. However, existing methods typically employ fixed and heuristic schemes to configure caching and pruning strategies. While they roughly follow the overall sensitivity trend of generation models to acceleration, they fail to capture fine-grained and complex variations, inevitably skipping highly sensitive computations and leading to quality degradation. Furthermore, such manually designed strategies exhibit poor generalization. To address these issues, we propose SODA, a Sensitivity-Oriented Dynamic Acceleration method that adaptively performs caching and pruning based on fine-grained sensitivity. SODA builds an offline sensitivity error modeling framework across timesteps, layers, and modules to capture the sensitivity to different acceleration operations. The cache intervals are optimized via dynamic programming with sensitivity error as the cost function, minimizing the impact of caching on model sensitivity. During pruning and cache reuse, SODA adaptively determines the pruning timing and rate to preserve computations of highly sensitive tokens, significantly enhancing generation fidelity. Extensive experiments on DiT-XL/2, PixArt-

α

, and OpenSora demonstrate that SODA achieves state-of-the-art generation fidelity under controllable acceleration ratios. Our code is released publicly at: https://github.com/leaves162/SODA.

Tong Shao, Yusen Fu, Guoying Sun +3

Harbin Institute of Technology, Shenzhen

Diffusion Model Inference Acceleration Diffusion-Based Image Generation Diffusion Transformer Diffusion Model Caching Token Pruning Video Diffusion Models

Mar 6, 2026

DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion Transformer (DC-DiT), which replaces fixed patchification with a learned encoder-router-decoder scaffold that adaptively compresses the 2D input into a shorter token sequence through a chunking mechanism learned end-to-end with diffusion training. DC-DiT allocates fewer tokens to predictable regions and noisy timesteps, and more tokens to detailed regions and later refinement stages, yielding meaningful spatial segmentations and timestep-adaptive compression schedules without supervision. Furthermore, the router provides an importance ordering over retained tokens, enabling elastic inference: a single checkpoint can be evaluated at flexible compute budgets with a smooth quality-compute tradeoff. Additionally, DC-DiT can be upcycled from pretrained DiT checkpoints and is also compatible with orthogonal dynamic computation approaches. On class-conditional ImageNet generation, DC-DiT reduces inference FLOPs by up to 36.8% and improves FID by up to 37.8% over DiT baselines, yielding a stronger quality--compute Pareto frontier across model scales, resolutions, and guidance settings. More broadly, these results suggest that adaptive tokenization is a general mechanism for making visual generation both more efficient and more flexible at inference time.

Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi +3

Advanced Micro Devices Inc. (AMD)

Adaptive Tokenization Diffusion Transformer Diffusion-Based Image Generation Diffusion Model Inference Acceleration Visual Token Compression

Mar 6, 2026

Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution

Diffusion transformer (DiT) architectures show great potential for real-world image super-resolution (Real-ISR). However, their computationally expensive iterative sampling necessitates one-step distillation. Existing one-step distillation methods struggle with Real-ISR on DiT. They suffer from fundamental trajectory mismatch and generate severe grid-like periodic artifacts. To tackle these challenges, we propose StrSR, a novel one-step adversarial distillation framework featuring spectral and trajectory regularization. Specifically, we propose an asymmetric discriminative distillation architecture to bridge the trajectory gap. Additionally, we design a frequency distribution matching strategy to effectively suppress DiT-specific periodic artifacts caused by high-frequency spectral leakage. Extensive experiments demonstrate that StrSR achieves state-of-the-art performance in Real-ISR, across both quantitative metrics and visual perception. The code and models will be released at https://github.com/jkwang28/StrSR .

Jingkai Wang, Yixin Tang, Jue Gong +6

Shanghai Jiao Tong University, China · Shenzhen Transsion Holdings Co., Ltd., China

Diffusion Transformer Diffusion Model Distillation Image Super-Resolution

Mar 6, 2026

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers

Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations: (i) training-based approaches inherit data bias and often degrade image quality, and (ii) current techniques struggle with occlusion order, limiting real-world usability. To address these issues, we propose LayerBind. By modeling regional generation as distinct layers and binding them during the generation, our method enables precise regional and occlusion controllability. Our motivation stems from the observation that spatial layout and occlusion are established at a very early denoising stage, suggesting that rearranging the early latent structure is sufficient to modify the final output. Building on this, we structure the scheme into two phases: instance initialization and subsequent semantic nursing. (1) First, leveraging the contextual sharing mechanism in multimodal joint attention, Layer-wise Instance Initialization creates per-instance branches that attend to their own regions while anchoring to the shared background. At a designated early step, these branches are fused according to the layer order to form a unified latent with a pre-established layout. (2) Then, Layer-wise Semantic Nursing reinforces regional details and maintains the occlusion order via a layer-wise attention enhancement. Specifically, a sequential layered attention path operates alongside the standard global path, with updates composited under a layer-transparency scheduler. LayerBind is training-free and plug-and-play, serving as a regional and occlusion controller across Diffusion Transformers. Beyond generation, it natively supports editable workflows, allowing for flexible modifications like changing instances or rearranging visible orders. Both qualitative and quantitative results demonstrate LayerBind's effectiveness, highlighting its strong potential for creative applications.

Ruidong Chen, Yancheng Bai, Xuanpu Zhang +6

Tianjin University · Independent Researcher

Controllable Image Generation Compositional T2I Generation Attention Control in Diffusion Models Diffusion Transformer

Mar 5, 2026

Accelerating Text-to-Video Generation with Calibrated Sparse Attention

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a significant fraction of token-to-token connections consistently yield negligible scores across various inputs, and their patterns often repeat across queries. Thus, the attention computation in these cases can be skipped with little to no effect on the result. This observation continues to hold for connections among local token blocks. Motivated by this, we introduce CalibAtt, a training-free method that accelerates video generation via calibrated sparse attention. CalibAtt performs an offline calibration pass that identifies block-level sparsity and repetition patterns that are stable across inputs, and compiles these patterns into optimized attention operations for each layer, head, and diffusion timestep. At inference time, we compute the selected input-dependent connections densely, and skip the unselected ones in a hardware-efficient manner. Extensive experiments on Wan 2.1 14B, Mochi 1, and few-step distilled models at various resolutions show that CalibAtt achieves up to 1.58x end-to-end speedup, outperforming existing training-free methods while maintaining video generation quality and text-video alignment.

Shai Yehezkel, Shahar Yadin, Noam Elata +2

Apple · Tel Aviv University

Diffusion Model Inference Acceleration T2V Generation Video Diffusion Models Sparse Attention Diffusion Transformer

Mar 5, 2026

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods accelerate DiTs by reusing intermediate computations across timesteps, but they share a common limitation: treating the denoising process as uniform across time,depth, and feature dimensions. In this work, we identify three orthogonal axes of non-uniformity in DiT denoising: (1) temporal -- sensitivity to caching errors varies dramatically across the denoising trajectory; (2) depth -- consecutive caching decisions lead to cascading approximation errors; and (3) feature -- different components of the hidden state exhibit heterogeneous temporal dynamics. Based on these observations, we propose SpectralCache, a unified caching framework comprising Timestep-Aware Dynamic Scheduling (TADS), Cumulative Error Budgets (CEB), and Frequency-Decomposed Caching (FDC). On FLUX.1-schnell at 512x512 resolution, SpectralCache achieves 2.46x speedup with LPIPS 0.217 and SSIM 0.727, outperforming TeaCache (2.12x, LPIPS 0.215, SSIM 0.734) by 16% in speed while maintaining comparable quality (LPIPS difference < 1%). Our approach is training-free, plug-and-play, and compatible with existing DiT architectures.

Guandong Li

iFLYTEK

Diffusion Model Caching Diffusion Model Inference Acceleration Diffusion Transformer Diffusion Timestep Scheduling

Mar 4, 2026

DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers

Recent breakthroughs in Diffusion Transformers (DiTs) have revolutionized the field of visual synthesis due to their superior scalability. To facilitate DiTs' capability of capturing meaningful internal representations, recent works such as REPA incorporate external pretrained encoders for representation alignment. However, the underlying mechanisms governing representation learning within DiTs are not well understood. To this end, we first systematically investigate the representation dynamics of DiTs. Through analyzing the evolution and influence of internal representations under various settings, we reveal that representation diversity across blocks is a crucial factor for effective learning. Based on this key insight, we propose DiverseDiT, a novel framework that explicitly promotes representation diversity. DiverseDiT incorporates long residual connections to diversify input representations across blocks and a representation diversity loss to encourage blocks to learn distinct features. Extensive experiments on ImageNet 256x256 and 512x512 demonstrate that our DiverseDiT yields consistent performance gains and convergence acceleration when applied to different backbones with various sizes, even when tested on the challenging one-step generation setting. Furthermore, we show that DiverseDiT is complementary to existing representation learning techniques, leading to further performance gains. Our work provides valuable insights into the representation learning dynamics of DiTs and offers a practical approach for enhancing their performance.

Mengping Yang, Zhiyu Tan, Binglei Li +3

Fudan University · Shanghai Academy of AI for Science · Shanghai Innovation Institute

Diffusion Transformer Diffusion Models Diffusion-Based Image Generation

Mar 3, 2026

COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data

Earth observation applications increasingly rely on data from multiple sensors, including optical, radar, elevation, and land-cover. Relationships between modalities are fundamental for data integration but are inherently non-injective: identical conditioning information can correspond to multiple physically plausible observations, and should be parametrised as conditional distributions. Deterministic models, by contrast, collapse toward conditional means and fail to represent the uncertainty and variability required for tasks such as data completion and cross-sensor translation. We introduce COP-GEN, a multimodal latent diffusion transformer that models the joint distribution of heterogeneous EO modalities at their native spatial resolutions. By parameterising cross-modal mappings as conditional distributions, COP-GEN enables flexible any-to-any conditional generation, including zero-shot modality translation without task-specific retraining. Experiments show that COP-GEN generates diverse yet physically consistent realisations while maintaining strong peak fidelity across optical, radar, and elevation modalities. Qualitative and quantitative analyses demonstrate that the model captures meaningful cross-modal structure and adapts its output uncertainty as conditioning information increases. We release a stochastic benchmark built from multi-temporal Sentinel-2 observations that enables distribution-level comparison of generative EO models. On this benchmark, COP-GEN covers 90% of the real observation manifold and 63% of its per-band reflectance range, while the strongest competing method collapses to 2.8% and 18%, respectively. These results highlight the importance of stochastic generative modeling for EO and motivate evaluation protocols beyond single-reference, pointwise metrics. Website: https://miquel-espinosa.github.io/cop-gen

Miguel Espinosa, Eva Gmelich Meijling, Valerio Marsocci +2

School of Engineering, University of Edinburgh · European Space Agency (ESA) · Asterisk Labs

Conditional Generative Modeling Multimodal Diffusion Models Remote Sensing Diffusion Transformer Remote Sensing Benchmarks

Mar 3, 2026

SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video quality due to high activation variation and the difficulty of preserving semantic and temporal coherence. We propose SemanticDialect, which advances block-wise mixed-format quantization. In this framework, each block selects an optimal format (dialect) from a candidate set (formatbook), which is augmented with lookup tables that store quantization errors and quantized indices, enabling efficient per-block format selection and quantization with minimal online overhead. We further introduce attention-guided activation decomposition, which reduces quantization error via residual quantization, and semantic-aware dialect assignment (SeDA), which reduces cross-token quantization inconsistency by enforcing format uniformity among semantically correlated tokens. Experiments demonstrate that SemanticDialect outperforms prior quantization methods and block-wise formats (MXFP4, NVFP4) while approaching FP16 quality on Open-Sora 2.0. We also validate hardware deployability through RTL design and GPU kernel implementation.

Wonsuk Jang, Thierry Tambe

Stanford University

Diffusion Model Quantization Neural Network Quantization Activation Quantization Video Diffusion Models Diffusion Transformer

Mar 2, 2026

TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis

We introduce TerraDiT, a diffusion transformer designed for text-to-satellite image generation with point-based control. Existing controlled satellite image generative models often require pixel-level maps that are time-consuming to acquire, yet semantically limited. To address this limitation, we introduce a novel point-based conditioning framework that controls the generation process through the spatial location of the points and the textual description associated with each point, providing semantically rich control signals. This approach enables flexible, annotation-friendly, and computationally simple inference for satellite image generation. To this end, we introduce an adaptive local attention mechanism that effectively regularizes the attention scores based on the input point queries. We systematically evaluate various domain-specific design choices for training TerraDiT, including the selection of satellite image representation for alignment and geolocation representation for conditioning. Our experiments demonstrate that TerraDiT achieves impressive generation performance, surpassing the state-of-the-art remote sensing generative models. Our models, dataset, and code are available at https://github.com/mvrl/TerraDiT.

Srikumar Sastry, Dan Cher, Brian Wei +4

Washington University, St. Louis MO 63130, USA

Diffusion Transformer Controllable Image Generation T2I Diffusion Models

Mar 2, 2026

Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism leads to explosive O(N^2) memory consumption and high first-frame latency. To address these issues, we implement system-level inference optimizations for a causal autoregressive video generation pipeline. We adapt the Self-Forcing causal autoregressive framework to sequence parallel inference and implement a sequence-parallel variant of the causal rotary position embedding which we refer to as Causal-RoPE SP. This adaptation enables localized computation and reduces cross-rank communication in sequence parallel execution. In addition, computation and communication pipelines are optimized through operator fusion and RoPE precomputation. Experiments conducted on an eight GPU A800 cluster show that the optimized system achieves comparable generation quality, sub-second first-frame latency, and near real-time inference speed. For generating five second 480P videos, a 1.58x speedup is achieved, thereby providing effective support for real-time interactive applications.

Chao Yuan, Pan Li

Diffusion Model Inference Acceleration Autoregressive Video Generation Diffusion Transformer Rotary Positional Embeddings

Mar 2, 2026

Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation

Text-to-audio (T2A) generation has advanced considerably in recent years, yet existing methods continue to face challenges in accurately rendering complex text prompts, particularly those involving intricate audio effects, and achieving precise text-audio alignment. While prior approaches have explored data augmentation, explicit timing conditioning, and reinforcement learning, overall synthesis quality remains constrained. In this work, we experiment with reinforcement learning to further enhance T2A generation quality, building on diffusion transformer (DiT)-based architectures. Our method first employs a large language model (LLM) to generate high-fidelity, richly detailed audio captions, substantially improving text-audio semantic alignment, especially for ambiguous or underspecified prompts. We then apply Group Relative Policy Optimization (GRPO), a recently introduced reinforcement learning algorithm, to fine-tune the T2A model. Through systematic experimentation with diverse reward functions (including CLAP, KL, FAD, and their combinations), we identify the key drivers of effective RL in audio synthesis and analyze how reward design impacts final audio quality. Experimental results demonstrate that GRPO-based fine-tuning yield substantial gains in synthesis fidelity and prompt adherence.

Yi Gu, Yanqing Liu, Chen Yang +1

Tsinghua University · Microsoft

Text-to-Audio Generation RL for Diffusion Models Group Relative Policy Optimization Diffusion Transformer

Feb 28, 2026

Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness

Diffusion models have achieved remarkable success in generative AI, yet their computational efficiency remains a significant challenge, particularly for Diffusion Transformers (DiTs) requiring intensive full-attention computation. While existing acceleration approaches focus on content-agnostic uniform optimization strategies, we observe that different regions in generated content exhibit heterogeneous convergence patterns during the denoising process. We present Jano, a training-free framework that leverages this insight for efficient region-aware generation. Jano introduces an early-stage complexity recognition algorithm that accurately identifies regional convergence requirements within initial denoising steps, coupled with an adaptive token scheduling runtime that optimizes computational resource allocation. Through comprehensive evaluation on state-of-the-art models, Jano achieves substantial acceleration (average 2.0 times speedup, up to 2.4 times) while preserving generation quality. Our work challenges conventional uniform processing assumptions and provides a practical solution for accelerating large-scale content generation. The source code of our implementation is available at https://github.com/chen-yy20/Jano.

Yuyang Chen, Linqian Zeng, Yijin ZHou +2

Shanghai Jiaotong University · Tsinghua University

Diffusion Timestep Scheduling Diffusion Model Inference Acceleration Diffusion Models Diffusion Transformer

Feb 26, 2026

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces

Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matrix dimensions. Generation is further complicated by permutation symmetries that allow networks to model similar input-output functions while having widely different, unaligned parameterizations. In this work, we introduce Neural Network Diffusion Transformers (NNiTs), which generate weights in a width-agnostic manner by tokenizing weight matrices into patches and modeling them as locally structured fields. We establish that Graph HyperNetworks (GHNs) with a convolutional neural network (CNN) decoder structurally align the weight space, creating the local correlation necessary for patch-based processing. Focusing on Multilayer Perceptrons (MLPs), where permutation symmetry is especially apparent, NNiTs generate fully functional networks across a range of architectures. Our approach jointly models discrete architecture tokens and continuous weight patches within a single sequence model. On ManiSkill3 robotics tasks, NNiT achieves

>85\%

success on architecture topologies unseen during training, while baseline approaches fail to generalize; the same pipeline also generalizes to MNIST classification beyond the robotic control setting.

Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu +3

Department of Electrical and Computer Engineering, Duke University, NC, USA · Department of Computer Science, Duke University, NC, USA · Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, MA, USA

Diffusion Transformer Neural Network Generalization

Feb 25, 2026

Absorbing Discrete Diffusion for Speech Enhancement

Inspired by recent developments in neural speech coding and diffusion-based language modeling, we tackle speech enhancement by modeling the conditional distribution of clean speech codes given noisy speech codes using absorbing discrete diffusion. The proposed approach, which we call ADDSE, leverages both the expressive latent space of neural audio codecs and the non-autoregressive sampling procedure of diffusion models. To efficiently model the hierarchical structure of residual vector quantization codes, we propose RQDiT, which combines techniques from RQ-Transformer and diffusion Transformers for non-autoregressive modeling. Results show competitive performance in terms of non-intrusive objective metrics on two datasets, especially at low signal-to-noise ratios and with few sampling steps. Code and audio examples are available online.

Philippe Gonzalez

Department of Health Technology, Technical University of Denmark

Speech Enhancement Diffusion Models Diffusion Transformer

Feb 25, 2026

A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers

Diffusion Transformers have achieved state-of-the-art performance in class-conditional and multimodal generation, yet the structure of their learned conditional embeddings remains poorly understood. In this work, we present the first systematic study of these embeddings and uncover a notable redundancy: class-conditioned embeddings exhibit extreme angular similarity, exceeding 99% on ImageNet-1K, while continuous-condition tasks such as pose-guided image generation and video-to-audio generation reach over 99.9%. We further find that semantic information is concentrated in a small subset of dimensions, with head dimensions carrying the dominant signal and tail dimensions contributing minimally. By pruning low-magnitude dimensions--removing up to two-thirds of the embedding space--we show that generation quality and fidelity remain largely unaffected, and in some cases improve. These results reveal a semantic bottleneck in Transformer-based diffusion models, providing new insights into how semantics are encoded and suggesting opportunities for more efficient conditioning mechanisms.

Trung X. Pham, Kang Zhang, Ji Woo Hong +1

Korea Advanced Institute of Science and Technology (KAIST)

Diffusion Transformer Conditional Diffusion Models

Feb 24, 2026

LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods based on simple reusing or training-free forecasting struggle to adapt to the complex, stage-dependent dynamics of the diffusion process, often resulting in quality degradation and failing to maintain consistency with the standard denoising process. To address this, we propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training. Our approach leverages a Kolmogorov-Arnold Network (KAN) to accurately learn temporal feature mappings from data. We further introduce a multi-stage, multi-expert architecture that assigns specialized predictors to different noise-level stages, enabling more precise and robust feature forecasting. Extensive experiments show our method achieves significant acceleration while maintaining high-fidelity generation. Experiments demonstrate 5.00x acceleration on FLUX.1-dev with minimal quality degradation (1.0% drop), 6.25x speedup on Qwen-Image with a 20.2% quality improvement over the previous SOTA (TaylorSeer), and 5.00x acceleration on HunyuanVideo with a 24.7% PSNR improvement over TaylorSeer. State-of-the-art performance on both text-to-image and text-to-video synthesis validates the effectiveness and generalization capability of our training-based framework across different models. Our code is available at https://github.com/caipeiliang2004/LESA.

Peiliang Cai, Jiacheng Liu, Haowen Xu +3

Shanghai Jiao Tong University

Diffusion Model Inference Acceleration Diffusion Models Diffusion Model Caching T2I Diffusion Models Diffusion Transformer Video Diffusion Models

Feb 23, 2026

Relational Feature Caching for Accelerating Diffusion Transformers

Feature caching approaches accelerate diffusion transformers (DiTs) by storing the output features of computationally expensive modules at certain timesteps, and exploiting them for subsequent steps to reduce redundant computations. Recent forecasting-based caching approaches employ temporal extrapolation techniques to approximate the output features with cached ones. Although effective, relying exclusively on temporal extrapolation still suffers from significant prediction errors, leading to performance degradation. Through a detailed analysis, we find that 1) these errors stem from the irregular magnitude of changes in the output features, and 2) an input feature of a module is strongly correlated with the corresponding output. Based on this, we propose relational feature caching (RFC), a novel framework that leverages the input-output relationship to enhance the accuracy of the feature prediction. Specifically, we introduce relational feature estimation (RFE) to estimate the magnitude of changes in the output features from the inputs, enabling more accurate feature predictions. We also present relational cache scheduling (RCS), which estimates the prediction errors using the input features and performs full computations only when the errors are expected to be substantial. Extensive experiments across various DiT models demonstrate that RFC consistently outperforms prior approaches significantly. Project page is available at https://cvlab.yonsei.ac.kr/projects/RFC

Byunggwan Son, Jeimin Jeon, Jeongwoo Choi +1

Yonsei University · Korea Institute of Science and Technology (KIST)

Diffusion Model Caching Diffusion Model Inference Acceleration Diffusion Transformer

Feb 20, 2026

Exploiting Completeness Perception with Diffusion Transformer for Unified 3D MRI Synthesis

Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in clinical practice. Existing methods rely on external guidance to supply detailed missing-state information for instructing generative models to synthesize missing MRIs. However, manual indicators are not always available or reliable in real-world scenarios due to the unpredictable nature of clinical environments. Moreover, these explicit masks are not informative enough to provide guidance for improving semantic consistency. In this work, we argue that generative models should infer and recognize missing states in a self-perceptive manner, enabling them to better capture subtle anatomical and pathological variations. Towards this goal, we propose CoPeDiT, a shared completeness-perception framework for 3D MRI synthesis, following a common conditioning strategy with task-specific instantiations for different missing-data scenarios. Specifically, we incorporate dedicated pretext tasks into our tokenizer, CoPeVAE, empowering it to learn completeness-aware discriminative prompt tokens, and design MDiT3D, a specialized diffusion transformer architecture for 3D MRI synthesis that effectively uses the completeness-aware prompt tokens as guidance to enhance semantic consistency in 3D space. Comprehensive evaluations on three large-scale MRI datasets demonstrate that CoPeDiT consistently improves upon state-of-the-art methods across diverse missing patterns, yielding high-fidelity and structurally consistent MRI synthesis. Our code is available at https://github.com/JK-Liu7/CoPeDiT.

Junkai Liu, Nay Aung, Theodoros N. Arvanitis +3

School of Engineering, University of Birmingham, UK · William Harvey Research Institute, Queen Mary University London, UK · Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, UK +1

Medical Image Synthesis 3D Medical Imaging Learning with Missing Data Diffusion Transformer

Feb 20, 2026

Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose PrediT, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to

5.54\times

latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.

Hanshuai Cui, Zhiqing Tang, Qianli Ma +3

School of Artificial Intelligence, Beijing Normal University, Beijing, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China · Shenzhen University of Advanced Technology, Shenzhen, China

Diffusion Model Acceleration Diffusion Sampling Diffusion-Based Image Generation Diffusion Transformer Video Diffusion Models

Feb 20, 2026

Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers

Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key space to modulate attention routing, leaving the Value space -- which governs feature aggregation -- entirely unexploited. In this paper, we first reveal that both Key and Value projections in DiT's multi-modal attention layers exhibit a pronounced bias-delta structure, where token embeddings cluster tightly around a layer-specific bias vector. Building on this observation, we propose Dual-Channel Attention Guidance (DCAG), a training-free framework that simultaneously manipulates both the Key channel (controlling where to attend) and the Value channel (controlling what to aggregate). We provide a theoretical analysis showing that the Key channel operates through the nonlinear softmax function, acting as a coarse control knob, while the Value channel operates through linear weighted summation, serving as a fine-grained complement. Together, the two-dimensional parameter space

(δ_k, δ_v)

enables more precise editing-fidelity trade-offs than any single-channel method. Extensive experiments on the PIE-Bench benchmark (700 images, 10 editing categories) demonstrate that DCAG consistently outperforms Key-only guidance across all fidelity metrics, with the most significant improvements observed in localized editing tasks such as object deletion (4.9% LPIPS reduction) and object addition (3.2% LPIPS reduction).

Guandong Li

iFLYTEK

Diffusion-Based Image Editing Diffusion Model Guidance Attention Control in Diffusion Models Diffusion Transformer

Feb 19, 2026

CORAL: Correspondence Alignment for Improved Virtual Try-On

Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required. These methods do not explicitly enforce person-garment alignment and fail to explain how correspondence emerges within Diffusion Transformers (DiTs). In this paper, we first analyze full 3D attention in DiT-based architecture and reveal that the person-garment correspondence critically depends on precise person-garment query-key matching within the full 3D attention. Building on this insight, we then introduce CORrespondence ALignment (CORAL), a DiT-based framework that explicitly aligns query-key matching with robust external correspondences. CORAL integrates two complementary components: a correspondence distillation loss that aligns reliable matches with person-garment attention, and an entropy minimization loss that sharpens the attention distribution. We further propose a VLM-based evaluation protocol to better reflect human preference. CORAL consistently improves over the baseline, enhancing both global shape transfer and local detail preservation. Extensive ablations validate our design choices.

Jiyoung Kim, Youngjin Shin, Siyoon Jin +6

KAIST AI · NC AI Co., Ltd.

Virtual Try-On Diffusion Model Alignment Diffusion Transformer Semantic Correspondence