Diffusion Transformer

Also known as DiT

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 169% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 297

Jul 23, 2026cs.CV

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared state difficult to maintain in multi-agent and multi-view settings. We present WorldWeaver (W^2), a streaming multi-agent video diffusion model that augments rollout with cross-agent world state registers: learnable tokens that store shared world information, track individual agent status, and are dynamically updated after each generated chunk. We ground these registers with supervision signals spanning individual agent status, global state views including bird's-eye views, and scene text. We further improve the architecture with a Mixture-of-Transformers design that uses separate weights for world state modeling and visual frame modeling. Extensive experiments in two-agent Minecraft video generation show that explicit world-state modeling improves logical consistency and generation quality.

Sicheng Mo, Yuheng Li, Ziyang Leng +2

University of California, Los Angeles · Adobe Research

Diffusion Transformer Memory-Augmented Video Generation Autoregressive Video Generation Video World Models

Jul 23, 2026cs.LG

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standard fix applies an invertible linear transform to the activations and its inverse to the weights before quantizing both. Normalization layers between blocks force this transform to run online at every denoising step, making its inference computation cost the binding design constraint. Existing options trade quantization quality for inference cost: per-channel scaling (SmoothQuant) is computationally cheap but impacts the magnitude of the channels, which can harm quantization accuracy; fixed Hadamard transforms yield better quantization accuracy but require large block sizes that incur a high online cost; learned full-

d

invertible transforms calibrate best but entail a prohibitive dense

d \times d

matrix multiplication (GEMM) per layer per step. We propose KroQuant, a PTQ method that applies a learned Kronecker-structured invertible transform to each 32-element block of the activation, storing less than half the parameters of per-channel scaling. The block-local structure runs as small tensor-core GEMMs, and on an MI350 GPU the KroQuant quantizer kernel is up to

14\%

faster than the SmoothQuant kernel. Offline LoRaQ weight calibration then absorbs the residual per-weight quantization error. On PixArt-

Σ

, SANA, and FLUX.1-schnell at W4A4 (MXFP4e2), KroQuant produces outputs closer to the FP reference than SVDQuant and LoRaQ on MJHQ-30K and SDCI, while preserving or improving image quality.

Yann Bouquet, Alireza Khodamoradi, Kristof Denolf +1

EPFL, Lausanne, Switzerland. · Advanced Micro Devices, Inc., Longmont, CO, USA.

Diffusion Transformer Diffusion Model Quantization 4-Bit Quantization Activation Quantization Post-Training Quantization Neural Network Quantization

Jul 23, 2026cs.CV

PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing

Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content. Existing training-free editors either localize edits from terminal predictions under source and target prompts or preserve unrelated content through spatially unselective source-feature reuse without explicit region discovery. Before reaching the terminal predictions, prompt-induced semantic differences undergo additional network transformations that may obscure their spatial localization, reducing localization precision. Spatially unselective feature reuse forces a trade-off between edit completeness and background preservation. Therefore, we propose PC-Edit, a prompt-contrastive framework for training-free MM-DiT editing. PC-Edit contrasts the image-token attention outputs under the source and target prompts, capturing prompt-induced semantic differences directly where text-conditioned information is delivered to image tokens. The same contrast identifies a source-erasure region during inversion and a target-emergence region during denoising. Their union suppresses source remnants while allowing the target object to form naturally. PC-Edit further couples region discovery and background preservation within each sampling step by estimating the current edit region from preceding attention blocks and immediately injecting cached source K/V features outside it in subsequent blocks, thereby protecting unrelated content before the latent update. Experiments on PIE-Bench and our EditRegion-Bench, with human-verified edit-region annotations for single- and multi-object addition and replacement, show that PC-Edit achieves the best editing quality and background preservation among methods without user-specified edit regions.

Jian Zhang, Zhijun Zhang

School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China

Diffusion Transformer Text-Guided Image Editing Diffusion-Based Image Editing Image Editing

Jul 23, 2026stat.ML

Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting

The modeling of hydrometeorological time series with limited observations is a key challenge in the monitoring of hydro-systems and water resources, as well as for flood or drought risk assessment. Due to the high variability of the underlying processes and the sparsity of available measurements, traditional statistical approaches often struggle to accurately represent their dynamics. In this context, recent advances in deep learning offer a promising direction for improving the representation and generation of complex temporal processes sampled at several observation sites. This study investigates the application of transformer-based diffusion models to the simulation and reconstruction of hydrological time series. The proposed framework is applied to the joint modeling of water quantity and quality at six sites spread across three adjacent headwater catchments located in North-East France on a limestone plateau covered by forests and field crops. The model is calibrated and validated using available observational data, which has been quality controlled and corrected for sensor drift and malfunction through collaborative efforts by LNE metrology expertise and Andra monthly quality control over more than 15 years. Its performance is compared with several established baseline approaches commonly used for time series modeling. Quantitative evaluation metrics are employed to assess the ability of the proposed method to reproduce key temporal characteristics of the observed signals in two settings: the imputation of incomplete time series and the forecasting of upcoming hydrological conditions. Results support the effectiveness of the transformer-based approach and highlight its capacity to capture and simulate the complex patterns present in hydrological data. In particular, the results indicate that diffusion models can efficiently sample realistic time series distributions under observation settings with variable missing data for both forecasting and imputation.

Ferdinand Bhavsar, Lionel Benoit, Maxime Savatier +1

INRAE · Biostatistics and Spatial Processes (BioSP), INRAE, Avignon 84914, France · ANDRA +1

Multivariate Time Series Forecasting Time Series Imputation Diffusion Transformer Time Series Forecasting Probabilistic Time Series Forecasting

Jul 23, 2026cs.CV

MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Despite advances in full-face editing by diffusion-based methods, strong regional controllability, makeup fidelity, and identity preservation remain challenging. The reasons are (i) pixel-to-attention misalignment that causes spillover into non-target areas and weakens regional control; (ii) unclear transfer/preservation concept separation under two-image conditioning, leading to coupling between makeup attributes and identity; and (iii) the lack of a high-resolution dataset that is identity-consistent and region-labeled for fine-grained supervision. In this paper, we propose MagicMakeup, a diffusion transformer-based framework for region-controllable and high-fidelity makeup transfer, built on spatial constraints and concept disentanglement. To enable precise region-specific editing while preserving identity, we propose Token-Aligned Region Gating, which aligns pixel masks with attention and applies region-specific logit gating. To clarify the concepts of transfer and preservation, we further introduce Cross-Modal Perception Guidance, which aligns text and image features to enhance cross-modal concept perception. We also design a pipeline for the generation of 1024 x 1024 data pairs through region-specific makeup removal and establish a unified benchmark in synthetic and real settings. Extensive quantitative and qualitative experiments show that MagicMakeup improves regional controllability, makeup fidelity, and identity preservation, with strong robustness across styles, races, and poses.

Ziyi Wang, Siming Zheng, Yang Yang +5

State Key Lab of CAD&CG, Zhejiang University, China · vivo BlueImage Lab, vivo Mobile Communication Co., Ltd., China

Diffusion Transformer Image Style Transfer Diffusion-Based Image Editing Image Editing

Jul 22, 2026cs.CV

STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching

Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, collapsing the multimodal distribution modeling into a single-point estimation. This formulation suffers from a regression-to-mean bias, frequently struggling with ambiguous regions. In contrast, we introduce a prior-guided generative framework that integrates deterministic matching regression and generative distribution modeling within a complementary formulation. Built upon this formulation, we introduce StereoFlow through three key components: (i) a two-stage progressive cascade matching network that progressively produces multi-resolution stereo conditions with complementary matching cues; (ii) a pixel diffusion transformer (termed StereoDiT) with a frequency-decoupled architecture for modeling correspondence ambiguity; (iii) a few-step flow matching objective (termed Transition Flow Matching) for efficient optimization. In summary, \textsc{\textbf{StereoFlow}} achieves strong geometric consistency and rich fine-grained details in ill-posed, discontinuous regions and under zero-shot generalization. Extensive experiments demonstrate that the proposed StereoFlow establishes multiple state-of-the-art results across benchmarks, including Scene Flow, KITTI, ETH3D, and Middlebury.

Hao Wang, Haoran Geng, Xiaotong Yang +7

School of Computer Science and Engineering, Beihang University, Beijing 100191, China · Google · State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China +3

Flow Matching Diffusion Transformer Stereo Matching

Jul 21, 2026cs.CV

Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone. Diffusion Transformers (DiTs) can natively ingest heterogeneous tokens stemming from texts and images, but they lack mechanisms for determining where and how these tokens should influence the output. We introduce appearance pointers, compact tokens that guide DiTs toward the correct appearance cues at the correct spatial locations by aligning text or image inputs with user-specified masks. Appearance pointers are produced by a region correspondence network and refined through a spatial aggregation mechanism, enabling the model to handle multiple regional descriptions without significantly increasing token load. Our approach introduces the first modality-agnostic interface for localized multimodal control in a DiT without retraining the base model from scratch. Across a range of metrics, our single model reaches or surpasses the performance of modality-specific state of the art methods, offering a simple and extensible path toward precise, region-aware, multimodal guidance in generative image synthesis.

Rahul Sajnani, Yulia Gryaditskaya, Radomír Měch +2

1Brown University · 2Adobe Research

Diffusion Transformer Conditional Image Generation Diffusion Guidance Controllable Image Generation Multimodal Diffusion Models

Jul 21, 2026cs.CV

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers

Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scale DiTs, the conditioning input contains not only the user prompt but also chat-template tokens introduced by LLM-based text encoders. Yet how these tokens participate in the denoising computation remains poorly understood. To probe this, we introduce a causal interpretability framework. Using it to separate prompt-content tokens from chat-template tokens, we find that the template tokens carry little prompt-specific information at the encoder output. Yet surprisingly, they emerge as dominant image-to-text attention sinks and causally maintain object identity inside the DiT, acting as implicit semantic registers. We show that they acquire this identity indirectly. Rather than reading the prompt tokens, they draw the identity from the image latents into which the prompt semantics have already been injected at the very first layer. We further reveal a division of labor across heads and depth in DiTs, where distinct heads route semantics or render visual structure, and identity is committed in early blocks, carried by middle blocks, and refined in late ones. As a practical payoff, this analysis yields a training-free pruning rule that removes the causally inert prompt-reading heads and cuts

20\%

of joint-attention FLOPs at a

1.4

-point cost in GenEval accuracy. Overall, our work not only reveals that the tokens encoding semantics at the input need not be those that maintain them during generation, but also provides a causal view of internal mechanisms in diffusion transformers.

Maohua Li, Qirui Li, Yanke Zhou +10

Nanjing University · Alibaba Group · Zhejiang University

Transformer Interpretability Diffusion Transformer Attention Sinks Attention Head Pruning T2I Diffusion Models

Jul 21, 2026cs.CV

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation and instruction-based image editing. The stack is built from two co-designed components: Mage-VAE, a lightweight high-fidelity latent tokenizer, and a Native-Resolution Multimodal Diffusion Transformer trained with rectified flow matching. Mage-VAE uses one-step diffusion-style encoding and decoding with anchor-latent regularization, preserving the reconstruction quality of strong public VAEs while reducing tokenization cost by more than an order of magnitude. Together with native-resolution packing and stack-level CUDA kernel fusion, the stack supports flexible-resolution training and improves end-to-end training throughput by about

2.5\times

. Built on this foundation, we develop a complete model family with Base, RL-aligned, and Turbo variants for both generation and editing. Diffusion-NFT improves prompt following, text rendering, aesthetic quality, and editing fidelity, while few-step distillation with adversarial perceptual guidance produces 4-step Turbo models for low-latency inference. Despite its compact scale, Mage-Flow and Mage-Flow-Edit achieves competitive performance across standard generation and editing benchmarks. More importantly, the Turbo variants make high-resolution generation and editing practical for interactive use: at

1024^2

resolution on a single NVIDIA A100 GPU, Mage-Flow-Turbo generates an image in 0.59s, and Mage-Flow-Edit-Turbo edits an image in 1.02s, while maintaining a small memory footprint. These results show that careful tokenizer--backbone--system co-design can deliver strong high-resolution generation and editing within an efficient 4B model family.

Xinjie Zhang, Peng Zhang, Shicheng Zheng +21

Microsoft Mage Team

Diffusion Transformer Flow-Based Generative Modeling Diffusion Model Acceleration Diffusion-Based Image Editing T2I Diffusion Models

Jul 20, 2026cs.CV

DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer

Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \textbf{DuSPiT}, a \textbf{Du}al-branch \textbf{S}ub\textbf{P}atch \textbf{Pi}xel \textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention. Our results show that DuSPiT generates images with richer details and stronger fine-grained structures, while also achieving a better quality--efficiency trade-off than prior pixel-space diffusion transformers.

Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi

The University of Texas at Austin · Reve

Diffusion Transformer Pixel-Space Diffusion Models Diffusion-Based Image Generation

Jul 20, 2026cs.CV

Pixel-Space Diffusion Transformers

Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine textures and structural details, while separate representation and diffusion training creates a mismatch between reconstruction and generation objectives. These limitations have renewed interest in pixel-space diffusion, which models raw pixels directly, removes the VAE bottleneck, and supports end-to-end optimization. This formulation better matches the demands of high-fidelity generation but introduces challenges in high-dimensional modeling, including noise scheduling, loss weighting, token efficiency, and scalable architecture design. Pixel-space modeling also offers a promising basis for unified multimodal systems: raw pixels, text, and task conditions can be represented in a shared token space and jointly processed by a single Transformer, narrowing the gap between visual understanding and generation. This paper reviews Pixel-Space Diffusion Transformers (pDiTs) from the perspectives of model architecture, continuous generative mechanisms, and unified multimodal modeling. We summarize representative methods, identify key technical challenges, and discuss future directions toward high-fidelity, end-to-end vision foundation models that integrate generation and understanding.

Renye Yan, Jikang Cheng, You Wu +8

Peking University, China · Nanjing University, China · Stanford University, USA +3

Diffusion Transformer Pixel-Space Diffusion Models Diffusion-Based Image Generation Multimodal Diffusion Models

Jul 20, 2026cs.LG

JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive. Training-free DiT inference acceleration methods (e.g.,

Δ

-DiT, ScalingCache) exploit the fact that DiT hidden states and velocity predictions vary \emph{smoothly and nearly linearly} along the trajectory. We ask whether the same linearity can reduce the backward-pass cost of DiT RL training, and answer affirmatively with \textbf{JAGG} (\textbf{J}acobian-\textbf{A}ggregated \textbf{G}roup \textbf{G}radient), which reduces full transformer backward passes from

W

to

2

per group of

W

consecutive steps. JAGG approximates intermediate-step Jacobians via

t

-weighted interpolation of the endpoint Jacobians, then aggregates per-step upstream signals into two composite gradients applied through a single joint backward pass. We prove this interpolation is \emph{exact} when the velocity is linear in

(z,t)

, and a cosine-similarity routing rule (\texttt{jagg_frac}) deploys JAGG only where the assumption holds. Experiments on T2I benchmarks show JAGG delivers

\sim

2

\times

backward speedup with negligible quality degradation. The code for this work can be accessed through https://github.com/SchumiDing/JAGG.

Ruiyi Ding, Jie Li, He Kang +3

1KlingAI Research · University of Science and Technology of China · 2Fudan University +2

Backpropagation Diffusion Transformer T2I Generation Group Relative Policy Optimization RL for Diffusion Models Diffusion Model Acceleration

Jul 20, 2026cs.SD

FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration

Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.

Ali Boudaghi, Hadi Zare

Diffusion Model Inversion Diffusion Transformer Audio Editing Neural ODEs

Jul 17, 2026cs.CV

MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion

High-resolution video diffusion models built on Diffusion Transformers (DiTs) deliver strong fidelity but quickly exhaust the memory budget of a single workstation. A 100 billion-plus parameter DiT easily requires over a terabyte of persistent state, while naive spatiotemporal self-attention grows quadratically in sequence length. These two walls -- parameter memory and activation memory -- prevent researchers from adapting massive generative models without large GPU clusters. We revisit this problem from a systems perspective and introduce MegaSlide-DiT, a prototype that demonstrates how a pre-trained 105B DiT can be adapted on a single H200 GPU with 1.5 TB of host RAM. Our key insight is that the GPU need not own the model state: all persistent weights, master weights and optimizer moments remain in host memory, while only transient shards are streamed to the GPU on demand. Simultaneously, we replace quadratic global attention with 3D Deformable Slide Attention (3D-DSA), a motion-adaptive local attention operator that reduces both memory and computational complexity to linear in the sequence length. We report detailed memory accounting, execution traces and evaluation results to substantiate our design. MegaSlide-DiT does not claim to train a 105B model from scratch on a single GPU, nor does it magically solve bandwidth limits; rather, it offers a pragmatic path for full-parameter adaptation of massive video diffusion models on high-end workstations.

Jiacheng Liu, Jason Liu

Trendinsight Lab / UC San Diego

Video Diffusion Models Diffusion Transformer Diffusion Model Fine-Tuning Deformable Attention Memory-Efficient Training

Jul 17, 2026cs.CV

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-

p

routing creates uneven per-head workloads under multi-GPU sequence parallelism. The resulting workload heterogeneity turns sparse attention into a rank-level straggler problem. We present \method{}, a training-free sparse-attention system that improves the distributed execution efficiency of adaptive sparse attention under multi-GPU sequence parallelism. \method{} uses Top-

p

routing, a Top-

k

safety floor, and video-aware block organization as the sparse-routing frontend, then repairs the materialized mask at runtime. Runtime Load Balancing migrates a small number of heavy heads via P2P communication to shorten the current critical path. Slack-Aware Sparse Augmentation fills residual non-critical-rank slack with additional high-value blocks, while overlap hides scheduling and migration overhead behind existing computation. On step-distilled Wan2.2 I2V, \method{} reduces average load imbalance from 1.34 to 1.08 and delivers a

4.41\times

attention speedup over FlashAttention, while achieving a

2.02

--

2.11\times

DiT inference speedup with competitive video quality.

Hao Liu, Chenghuan Huang, Ye Huang +7

Sun Yat-sen University · WeChat HPC, Tencent Inc. · Peking University +1

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

Jul 17, 2026cs.CV

PE-Field 4D: Video Generation Models as Canvas

Diffusion Transformers have recently achieved strong performance in video generation, yet controlling scene geometry under viewpoint changes and camera motion remains challenging. In this work, we revisit the role of positional encoding in video diffusion transformers and show that it provides a useful spatial bias for geometry-aware control. Specifically, if reference tokens are encoded according to their projected locations in the target view, the denoising model is encouraged to retrieve content from position aligned regions of the input video. Building on this observation, we introduce a geometry-aware cross-attention mechanism that enables target video latent tokens to attend to structured context tokens derived from reference images or frames. To establish correspondence between the reference content and the target camera trajectory, we equip the context tokens with a projected positional encoding scheme that combines target-view 2D reprojection with depth-aware disambiguation. At the same time, we preserve the original spatiotemporal positional encoding of the generated video latent, allowing geometric guidance to be injected while maintaining consistency with the video model's native latent structure. The resulting framework provides a simple and effective approach for controllable video generation. It improves spatial controllability in viewpoint-dependent editing tasks, including camera re-trajectory, novel-view video synthesis, and geometry-aware video editing, while preserving the generative prior of the underlying video diffusion model. The code is available at: https://github.com/MTLab/PE-Field.

Yunpeng Bai, Haoxiang Li, Qixing Huang

University of Texas at Austin, USA · Pixocial Technology, USA

Camera-Controlled Video Generation Diffusion Transformer Dynamic Novel View Synthesis Video Generation Controllable Video Generation

Jul 17, 2026cs.CV

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse

Recent advances in AI-generated content have driven widespread adoption of Diffusion Transformers (DiTs) for high-resolution, long-duration content generation. While parallelization techniques accelerate diffusion inference, they face significant scalability challenges due to excessive communication overhead in multi-node environments. We observe that sequence partitions in Context Parallelism (CP) exhibit distinct heterogeneity: spatially proximate partitions contribute more significantly to attention computation results. By mapping this heterogeneous pattern to hierarchical communication topology, we can access high-contribution partitions with reduced communication cost. This insight motivates our novel selective attention state mechanism that strategically balances partial attention computation and historical result reuse across denoising steps. We present DiTango, an efficient parallel framework for DiT generation. DiTango features an anchor-guided state selection planner that optimizes computation-reuse decisions for each partition, complemented by a runtime that orchestrates efficient state-centric operations. This design achieves superior system efficiency while preserving generation quality. Experimental evaluation on popular diffusion models demonstrates that DiTango achieves up to 1.9x end-to-end and 3.2x attention speedup with near-linear scaling in multi-node settings, while maintaining generation quality comparable to state-of-the-art approaches.

Yuyang Chen, Runxin Zhong, Zan Zong +3

Shanghai Jiao Tong University, Shanghai AI Laboratory Shanghai, China · Tsinghua University Beijing, China · University of Science and Technology Beijing Beijing, China +1

Diffusion Transformer Efficient Attention Diffusion Model Caching Distributed Inference Diffusion Model Inference Acceleration

Jul 16, 2026cs.CV

Introspective Attention Modulation for Safe Text-to-Image Generation

State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range from concept erasure and prompt filtering to classifier-based gating. However, simple techniques like parameter efficient adaptations of the models easily bypass such guardrails. We introduce a unique principled approach that achieves safety by regulating the model's attention dynamics through inference-time introspection, exhibiting intrinsic robustness. Our method analyzes and rebalances attention activations throughout image synthesis, steering generations away from unsafe concepts while preserving semantic alignment. This introspective control ensures safety of deployed models. Across standard and adversarial safety benchmarks, our approach achieves remarkable safety scores while maintaining or even improving alignment and perceptual quality. Our results reveal that attention-space regulation offers a considerably more promising path to safer diffusion transformer based image generation than the existing concept erasing mechanism.Our code can be accessed at https://basim-azam.github.io/iam/

Basim Azam, Hossein Rahmani, Naveed Akhtar

The University of Melbourne, Australia · Lancaster University, United Kingdom

Diffusion Transformer T2I Generation Safe T2I Generation Attention Control in Diffusion Models Controllable Image Generation T2I Diffusion Models+1

Jul 15, 2026cs.AR

Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations

Video diffusion transformers (vDiTs) generate high quality video but introduce extremely high compute cost due to the long diffusion timesteps and self attention computation. As diffusion timesteps are reduced, the computation cost of self attention becomes the dominant bottleneck. Existing acceleration approaches largely inherit sparse attention techniques from large language models, which fail to consider the unique spatiotemporal correlation of video data. This paper presents Kaleido, an algorithm hardware codesign that accelerates all operations in vDiTs by exploiting channel-wise spatiotemporal correlations in latent space. Based on this insight, we propose a lightweight channelwise reuse algorithm that skips redundant computations by reusing partial results while preserving higher generative quality than prior methods (>17 dB). To efficiently support this algorithm, we design a systolic array like accelerator with reconfigurable processing elements and a lightweight data dispatcher to mitigate irregular sparsity and data access patterns introduced by our reuse algorithm. Evaluations across three mainstream vDiT models show that Kaleido achieves up to 5.9x speedup and 16.0x energy savings over state of the art accelerators.

Wenxuan Miao, Haosong Liu, Weiming Hu +9

Shanghai Jiao Tong University · Shanghai Jiao Tong University, Shanghai Qi Zhi Institute · Huawei Technologies +1

Video Diffusion Models Diffusion Transformer Hardware-Software Co-Design Diffusion Model Inference Acceleration

Jul 14, 2026cs.LG

ReDiTT: Retrieval Augmented Conditional Diffusion Transformers for Asynchronous Time Series

We present a diffusion based model for asynchronous time series prediction, where the goal is to predict the next inter event time and event type. To address the inherent uncertainty of future events, we introduce ReDiTT, a retrieval augmented conditional diffusion transformer that operates in latent space. ReDiTT retrieves structurally similar latent sequences from a memory bank during both training and inference and incorporates them as reference conditions through cross attention. This retrieval based conditioning allows the model to attend to relevant temporal dynamics and provides global structural guidance for generation. As a result, ReDiTT stabilizes long horizon forecasting and improves sample diversity. Experiments on seven real world datasets demonstrate state of the art performance on next event prediction and long horizon forecasting. Our code is available at https://github.com/BorealisAI/ReDiTT.

Saiyue Lyu, Zhitian Zhang, Ruizhi Deng +1

Department of Computer Science, University of British Columbia · Work done during an internship at RBC Borealis. · RBC Borealis

Irregular Time-Series Modeling Event Time Prediction Temporal Point Processes Diffusion Transformer Retrieval-Augmented Time Series Forecasting Conditional Diffusion Models

Jul 13, 2026cs.CV

Adaptive Routing for Efficient Diffusion Transformer-Based PNI Prediction

Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. However, its preoperative prediction from magnetic resonance imaging (MRI) remains challenging due to subtle imaging features that extend beyond tumor boundaries into surrounding regions. Conventional convolutional neural networks are limited in capturing long-range spatial dependencies. Transformer-based architectures improve global modeling of volumetric MRI by aggregating spatially distributed contextual cues, yet capturing subtle and noise-sensitive patterns in peritumoral regions remains challenging. Diffusion-based classifiers offer an alternative formulation by leveraging denoising-based class scoring to better capture such subtle patterns. However, these approaches introduce substantial computational overhead due to the combination of transformer-based modeling and iterative denoising processes. To address these challenges, we formulate PNI prediction as a diffusion-based classification problem and implement the denoising network using a transformer-based representation. To improve computational efficiency, we introduce adaptive routing across attention heads, spatial tokens, and MLP width. Experimental results demonstrate that the proposed approach achieves an AUC of 0.731 with 257.57 GFLOPs.

Youngung Han, Dohyun Kweon, Kyeonghun Kim +15

Seoul National University, Seoul, Republic of Korea · Kyung Hee University, Seoul, Republic of Korea · OUTTA, Seoul, Republic of Korea +5

Diffusion Transformer Medical Image Classification Clinical Prediction

Jul 13, 2026cs.CV

Controlling Motion Transfer in Diffusion Transformers via Attention Heads

Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs.

Sunyoung Jung, Jiwoo Park, Yoonseok Choi +3

Yonsei University · LG Electronics · University of California, Merced

Diffusion Model Guidance Diffusion Transformer Motion Retargeting Attention Mechanisms Controllable Video Generation

Jul 10, 2026cs.CL

FreyaTTS Technical Report

We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synthesis. Freya-TTS is a 183.2M-parameter non-autoregressive conditional flow-matching Diffusion Transformer (DiT) that operates in the frozen continuous latent space of AudioVAE2 (16 kHz encode, 48 kHz decode), allowing the model to focus its capacity on text-to-latent mapping while inheriting high-quality 48 kHz reconstruction. We advance the framework along three key dimensions: (1) rule-free end-to-end modeling from a 92-symbol Turkish character vocabulary without a phonemizer, grapheme-to-phoneme frontend, or discrete speech tokenizer; (2) non-autoregressive parallel denoising, which predicts the entire latent sequence simultaneously over a predicted duration; and (3) a production-oriented two-stage post-training recipe consisting of single-speaker voice locking and short-utterance coverage, improving speaker consistency and robustness on short inputs. On the Freya-TR-Eval benchmark, Freya-TTS achieves a band-matched word error rate (WER) of 8.0% and character error rate (CER) of 3.0%, outperforming substantially larger open-source systems while using a fraction of their parameters. The model achieves a real-time factor of 0.11 on consumer GPUs and runs faster than real time on a laptop CPU, making it well suited for resource-constrained edge deployment. We release the model weights, training and inference code, and evaluation benchmark under the Apache-2.0 license.

Ahmet Erdem Pamuk, Ömer Yentür, Ahmet Tunga Bayrak +2

Freya Team

Non-Autoregressive Text Generation TTS Synthesis Diffusion Transformer

Jul 9, 2026cs.CV

Multimodal 3D LUT Generation via StatLUT with Statistical Features for Photorealistic Style Transfer

Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained image encoders, leading to unnatural spatial distortions. Moreover, current pixel-level mapping paradigms often ignore color gamut topology, resulting in color banding, while also lacking the multimodal capability for intuitive text-driven control. To address these bottlenecks, we propose StatLUT, an innovative multimodal framework for 3D LUT generation. First, we bypass traditional encoders and introduce a Lab-Extractor to derive spatially-agnostic statistical features, fundamentally decoupling color distributions from structural semantics to ensure artifact-free rendering. Second, we formulate LUT generation as a Transformer-based Seq2Seq translation task, utilizing a Multi-dimensional Residual Mapper (MR-Mapper) to predict topologically smooth 3D LUTs. Finally, to break the single-modal barrier, we propose the H-Diffuser, a lightweight Diffusion Transformer that directly synthesizes statistical features from natural language prompts, enabling flexible text-driven color grading. Extensive experiments on standard benchmarks demonstrate that StatLUT significantly outperforms state-of-the-art methods in both visual quality and quantitative metrics, pioneering a highly robust and flexible paradigm for multimodal photorealistic style transfer.

Yifan Wang, Zhixiang Hao, Yu Wang +1

Honor Device Co., Ltd.

Diffusion Transformer Text-Guided Image Editing Image Style Transfer Multimodal Generation

Jul 9, 2026cs.IT

RadioDiff-v2: Generative Angular Radio Maps for Multi-Beam Selection and Localization

Angular radio maps describe the received-power distribution over the angle of arrival and underpin beam selection and receiver localization in sixth-generation (6G) networks. Predicting the angular power spectrum (APS) from geometry is difficult, because the mapping is ill-posed in non-line-of-sight (NLOS) conditions and must generalize to unseen environments. Distortion-minimizing regressors return the conditional mean, which over-smooths the spectrum and erases the multipath structure that downstream tasks need. We cast the task as a perception-distortion problem and propose RadioDiff-v2, a dual-branch one-dimensional diffusion transformer trained with flow matching. It couples periodic angular encoding, adaptive layer-normalization conditioning, a Fourier angular mixer, and joint velocity and clean-signal heads. A per-metric estimator portfolio reads every deployment quantity from this single model, so that samples carry the distribution, the clean-signal head supplies a regression-grade point estimate, Bayes-optimal rules select beams, and the conditional likelihood localizes the receiver. We prove that a concentrated conditional yields a straight probability-flow trajectory that one step integrates exactly, identifying deterministic transport as the correct inductive bias. On a zero-shot test of 99 environments and one million links, RadioDiff-v2 leads every baseline on every metric, with a 0.39 dB Wasserstein-1 distance, per-bin error below the regression baseline, a 2.43 dB eight-beam NLOS sweep loss, and a 20.6-pixel localization error with four base stations. Code is available at https://github.com/UNIC-Lab/RadioDiff-v2.

Xiucheng Wang, Junxi Huang, Nan Cheng

State Key Laboratory of ISN and School of Telecommunications Engineering, Xidian University, Xi’an 710071, China

Diffusion Transformer 6G Networks Wireless Localization Radio Propagation Modeling Map-Based Localization

Jul 7, 2026cs.CV

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets. We argue this inherits more of the generative output interface than dense prediction requires: unlike RGB synthesis, dense prediction asks for pixel-correct, task-native fields on the same image plane, not new RGB content to be rendered. Our key observation is that a pretrained DiT already organizes RGB inputs through a patch-to-token-to-patch lattice on the image plane, so each token indexes a fixed output patch whose channels can carry task-native quantities instead of RGB appearance. We instantiate this as ReChannel: we keep the VAE encoder for the DiT's input distribution but drop the target-side decoder, adapt the frozen DiT with task LoRA, and map each token to its p x p x K_t pixel-space patch through a shared token-local linear head--about 33K parameters, no spatial mixing. Using FLUX-Klein, we evaluate on six dense prediction tasks and over a dozen benchmarks. This minimal interface sets new state-of-the-art on trimap-free matting, KITTI depth, and referring segmentation, and stays competitive on normals, saliency, and pose. In a matched 4B setting it is more accurate and 2.48x faster than an edit-plus-latent-decode counterpart--dense perception can benefit from generative pretraining without inheriting its output interface.

Zanyi Wang, Xin Lin, Haodong Li +2

1UCSD · 2HKUST

Diffusion Transformer Dense Prediction T2I Diffusion Models

Jul 3, 2026cs.LG

When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures

Diffusion architectures now encompass convolutional UNets as well as transformer-based designs such as Diffusion Transformers (DiTs), inspired by Vision Transformers (ViTs), yet the effects of structured geometric perturbations within these architectures remain poorly understood. We study this question through a unified framework that applies reflection-based elements of the dihedral group to intermediate hidden states as controlled internal interventions, contrasting geometrically consistent and inconsistent variants. Using activation-level diagnostics, including Self-Consistency Shift (SCS), Activation Mass Scatter (AMS), and Drift, we analyze feature stability and geometric drift. We find that consistent transformations improve stability, while inconsistent ones induce predictable, architecture-specific failures. In the main Stable Diffusion 2.1 U-Net study, we evaluate seven intervention modes over three seeds and complement the internal diagnostics with image-level FID, KID, CLIP score, and LPIPS diversity. Taken together with supporting ViT and controlled DiT analyses, these results establish geometric consistency as a key principle for stable hidden-state interventions in spatially structured vision and diffusion models.

Mojtaba Faramarzi, Alex Lamb, Irina Rish

University of Montreal, Canada · Mila - Quebec AI Institute · Tsinghua University +1

Diffusion Transformer Vision Transformer Diffusion Models

Jul 3, 2026cs.CV

FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers

Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit critical alignment vulnerabilities, systematically manifesting severe stereotype biases even under benign prompts. This poses a significant risk of algorithmic discrimination in deployed systems. Since most existing mitigation strategies were tailored for legacy U-Net architectures, the precise remediation of these vulnerabilities in MM-DiTs remains a critical open challenge. In this work, we first investigate the root cause of this vulnerability via mechanistic analysis. We reveal that bias representations in MM-DiTs are not uniformly distributed across depth, but are mediated by a sparse set of layers functioning as internal semantic binding hubs. These hubs exhibit a stage-wise propagation driving bias manifestation: early hubs establish the structural templates susceptible to bias, middle hubs actively extract core stereotypical concepts from textual conditioning, and late hubs globally solidify these biases through visual self-attention. Leveraging these architectural insights, we propose FairFlow, an intrinsic, mechanism-guided mitigation framework. FairFlow acts as an internal regulator by employing sparse steering: it learns attribute-specific fair directions and injects them exclusively at the identified semantic hubs within a constrained inference window. Evaluations on FLUX.1-dev and Stable Diffusion~3 demonstrate that FairFlow effectively neutralizes these stereotypical vulnerabilities across gender, race, and intersectional settings, achieving an optimal fairness-fidelity balance. With near-zero inference overhead and robustness to complex prompts, FairFlow provides a lightweight and practical bias mitigation for large-scale deployed MM-DiT systems. Code and datasets will be publicly released upon acceptance.

Chen Chen, Yuanmin Huang, Zhenfei Zhang +5

Fudan University Shanghai, China · East China University of Science and Technology Shanghai, China

Diffusion Model Alignment Diffusion Transformer T2I Generation Demographic Bias in T2I Models Activation Steering T2I Diffusion Models

Jul 3, 2026cs.CV

HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

Video Diffusion Transformers (VDiTs) have demonstrated significant capabilities in high-fidelity video generation. However, their ability to produce long-duration videos is fundamentally constrained by the quadratic complexity of the self-attention mechanism. Recent clustering-based sparse attention methods improve the quality-speed trade-off by grouping semantically similar tokens, but their practical efficiency remains limited by two bottlenecks: substantial clustering overhead and low CTA utilization caused by irregular cluster-induced blocks. We propose HyperVAttention (HVA), a training-free sparse attention framework that addresses both bottlenecks jointly. To reduce clustering overhead, we introduce 3D local-window clustering, which exploits the spatio-temporal locality of video tokens to restrict centroid search to fixed local neighborhoods, and implement it with a custom Triton kernel for efficient execution. We further propose a hybrid clustering strategy that performs full clustering only at anchor steps and updates only subset tokens at intermediate steps, leveraging the temporal stability of cluster assignments across denoising steps. To improve CTA utilization, we present hardware-aware cluster merging that minimizes CTA-aligned execution cost through parallel agglomerative merging, improving block density and approximation fidelity by utilizing idle tile capacity. Together, these components reduce clustering overhead, avoid redundant updates, and better align sparse attention with the fixed tile structure of modern GPU kernels. Experiments on Text-to-Video generation show that HVA establishes a new Pareto frontier for training-free sparse attention in video diffusion, reducing end-to-end latency by up to

2.13\times

while improving fidelity over existing training-free sparse attention baselines.

Dongyeun Lee, Amir Zandieh, Vahab Mirrokni +2

KAIST · Google Research

Video Diffusion Models Diffusion Transformer Sparse Attention Diffusion Model Inference Acceleration

Jul 3, 2026cs.CV

Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiTs) remain insufficiently understood. In this work, we systematically analyze MAs in representative DiTs and find that they are spatially distributed across image tokens while concentrated in a small set of fixed feature dimensions. We further show that these dimensions are closely aligned with AdaLN residual scaling factors and are primarily modulated by the denoising timestep rather than text conditions. This structure leads to two task-dependent effects: for generation, MAs are critical for fine-grained detail synthesis while having limited influence on global semantics; for understanding, their shared high-magnitude directions make raw DiT features overly similar across spatial tokens and weaken dense feature discrimination. Based on these findings, we introduce Eliciting Massive Activation (EMA), a training-free framework that leverages Massive Activations (MAs) as a unified modulation signal to improve both generative and representational capabilities of DiTs. For generation, EMA proposes MA-driven Detail G}uidance (DG), which suppresses MA dimensions to construct a detail-deficient counterfactual prediction and guides sampling toward finer visual details. DG further supports efficient partial-forward inference, integration with classifier-free guidance, and token-level Local DG for refining selected image regions. For understanding, EMA introduces MA-modulated REPresentation extraction (MREP), which uses pretrained AdaLN channel-wise modulation to reduce MA directional dominance and concatenates spatially normalized MA maps to preserve useful spatial structure. Extensive experiments demonstrate that EMA consistently improves both the generation quality and representation capability of DiTs.

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu +6

Shanghai Jiao Tong University, Shanghai, China · The University of Hong Kong, Hong Kong, China · Monash University, Melbourne, Australia +2

Visual Representation Learning Diffusion Transformer Diffusion Guidance Diffusion-Based Image Generation