Multimodal Diffusion Models

Ask about this topic

Overview

These models use information from one or more modalities—such as text, images, audio, video, motion, or sensor data—to generate or understand content in another modality or several at once. Common approaches include continuous latent diffusion and flow-matching transformers, discrete masked-token diffusion, and architectures that combine shared representations with modality-specific streams, cross-attention, or adapters. They are used for tasks ranging from text-guided image and video creation to audio-video synchronization, motion generation, medical imaging, and multimodal reasoning, with evaluation spanning benchmarks such as GenEval, MMMU, VBench, and HumanML3D. A central challenge is maintaining coherence and precise alignment across modalities while preserving each modality’s quality, supporting missing or noisy inputs, and keeping inference and evaluation practical.

Latest papers

CardsList

175 papers26 papers in the last four weeks, up 73% on the four weeks before. 0.2% of all new papers.

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 ModelingMultimodal Diffusion ModelsRemote SensingDiffusion TransformerRemote Sensing Benchmarks
AskPDF
Mar 1, 2026

LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model

We present LLaDA-o, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-diffusion models on multimodal understanding and generation benchmarks, and reaches 87.04 on DPG-Bench for text-to-image generation, supporting the effectiveness of unified omni diffusion modeling. Code is available at https://github.com/ML-GSAI/LLaDA-o.

Zebin You, Xiaolu Zhang, Jun Zhou +2

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +1

Diffusion ModelsMultimodal Diffusion ModelsUnified Multimodal ModelsMultimodal GenerationDiffusion Language ModelsDiffusion Language Model Decoding
AskPDF
Feb 26, 2026

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between two people engaging in conversation. We present DyaDiT, a multi-modal diffusion transformer that generates contextually appropriate human motion from dyadic audio signals. Trained on Seamless Interaction Dataset, DyaDiT takes dyadic audio with optional social-context tokens to produce context-appropriate motion. It fuses information from both speakers to capture interaction dynamics, uses a motion dictionary to encode motion priors, and can optionally utilize the conversational partner's gestures to produce more responsive motion. We evaluate DyaDiT on standard motion generation metrics and conduct quantitative user studies, demonstrating that it not only surpasses existing methods on objective metrics but is also strongly preferred by users, highlighting its robustness and socially favorable motion generation. Code and models will be released upon acceptance.

Yichen Peng, Jyun-Ting Song, Siyeol Jung +7

Institute of Science Tokyo · Carnegie Mellon Unversity · UNIST +2

Human Motion GenerationCo-Speech Gesture GenerationMotion Diffusion ModelsMultimodal Diffusion Models
AskPDF
Feb 25, 2026

SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model

SkyReels V4 is a unified multi modal video foundation model for joint video audio generation, inpainting, and editing. The model adopts a dual stream Multimodal Diffusion Transformer (MMDiT) architecture, where one branch synthesizes video and the other generates temporally aligned audio, while sharing a powerful text encoder based on the Multimodal Large Language Models (MLLM). SkyReels V4 accepts rich multi modal instructions, including text, images, video clips, masks, and audio references. By combining the MLLMs multi modal instruction following capability with in context learning in the video branch MMDiT, the model can inject fine grained visual guidance under complex conditioning, while the audio branch MMDiT simultaneously leverages audio references to guide sound generation. On the video side, we adopt a channel concatenation formulation that unifies a wide range of inpainting style tasks, such as image to video, video extension, and video editing under a single interface, and naturally extends to vision referenced inpainting and editing via multi modal prompts. SkyReels V4 supports up to 1080p resolution, 32 FPS, and 15 second duration, enabling high fidelity, multi shot, cinema level video generation with synchronized audio. To make such high resolution, long-duration generation computationally feasible, we introduce an efficiency strategy: Joint generation of low resolution full sequences and high-resolution keyframes, followed by dedicated super-resolution and frame interpolation models. To our knowledge, SkyReels V4 is the first video foundation model that simultaneously supports multi-modal input, joint video audio generation, and a unified treatment of generation, inpainting, and editing, while maintaining strong efficiency and quality at cinematic resolutions and durations.

Guibin Chen, Dixuan Lin, Jiangping Yang +48

Multimodal Video GenerationAudio-Video GenerationMultimodal Diffusion ModelsVideo EditingMulti-Shot Video GenerationLong Video Generation+1
AskPDF
Feb 25, 2026

The Design Space of Tri-Modal Masked Diffusion Models

Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal generation. Diverging from previous approaches, we introduce the first tri-modal masked diffusion model pretrained from scratch on text, image-text, and audio-text data. We systematically analyze multimodal scaling laws, modality mixing ratios, noise schedules, and batch-size effects, and we provide optimized inference sampling defaults. Our batch-size analysis yields a novel stochastic differential equation (SDE)-based reparameterization that eliminates the need for tuning the optimal batch size as reported in recent work. This reparameterization decouples the physical batch size, often chosen based on compute constraints (GPU saturation, FLOP efficiency, wall-clock time), from the logical batch size, chosen to balance gradient variance during stochastic optimization. Finally, we pretrain a preliminary 3B-parameter tri-modal model on 6.4T tokens, demonstrating the capabilities of a unified design and achieving strong results in text generation, text-to-image tasks, and text-to-speech tasks. Our work represents the largest-scale systematic open study of multimodal discrete diffusion models conducted to date, providing insights into scaling behaviors across multiple modalities.

Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec +21

Apple · University of Cambridge · MIT +1

Diffusion ModelsMultimodal Diffusion ModelsMasked Diffusion ModelsMultimodal PretrainingScaling Laws
AskPDF
Feb 24, 2026

RelA-Diffusion: Relativistic Adversarial Diffusion for Multi-Tracer PET Synthesis from Multi-Sequence MRI

Multi-tracer positron emission tomography (PET) provides critical insights into diverse neuropathological processes such as tau accumulation, neuroinflammation, and ββ-amyloid deposition in the brain, making it indispensable for comprehensive neurological assessment. However, routine acquisition of multi-tracer PET is limited by high costs, radiation exposure, and restricted tracer availability. Recent efforts have explored deep learning approaches for synthesizing PET images from structural MRI. While some methods rely solely on T1-weighted MRI, others incorporate additional sequences such as T2-FLAIR to improve pathological sensitivity. However, existing methods often struggle to capture fine-grained anatomical and pathological details, resulting in artifacts and unrealistic outputs. To this end, we propose RelA-Diffusion, a Relativistic Adversarial Diffusion framework for multi-tracer PET synthesis from multi-sequence MRI. By leveraging both T1-weighted and T2-FLAIR scans as complementary inputs, RelA-Diffusion captures richer structural information to guide image generation. To improve synthesis fidelity, we introduce a gradient-penalized relativistic adversarial loss to the intermediate clean predictions of the diffusion model. This loss compares real and generated images in a relative manner, encouraging the synthesis of more realistic local structures. Both the relativistic formulation and the gradient penalty contribute to stabilizing the training, while adversarial feedback at each diffusion timestep enables consistent refinement throughout the generation process. Extensive experiments on two datasets demonstrate that RelA-Diffusion outperforms existing methods in both visual fidelity and quantitative metrics, highlighting its potential for accurate synthesis of multi-tracer PET.

Minhui Yu, Yongheng Sun, David S. Lalush +3

Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. · Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill and North Carolina State University, Chapel Hill, NC 27599, USA. · Department of Exercise and Sport Science, UNC-CH, Chapel Hill, NC 27599, USA.

Medical Image SynthesisDiffusion ModelsMultimodal Diffusion Models
AskPDF
Feb 24, 2026

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that well-established data-poisoning pipelines can successfully implant backdoors into MDLMs, enabling attackers to manipulate model behavior via specific triggers while maintaining normal performance on clean inputs. However, defense strategies effective to these models are yet to emerge. To bridge this gap, we introduce a backdoor defense framework for MDLMs named DiSP (Diffusion Self-Purification). DiSP is driven by a key observation: selectively masking certain vision tokens at inference time can neutralize a backdoored model's trigger-induced behaviors and restore normal functionality. Building on this, we purify the poisoned dataset using the compromised model itself, then fine-tune the model on the purified data to recover it to a clean one. Given such a specific design, DiSP can remove backdoors without requiring any auxiliary models or clean reference data. Extensive experiments demonstrate that our approach effectively mitigates backdoor effects, reducing the attack success rate (ASR) from over 90% to typically under 5%, while maintaining model performance on benign tasks.

Guangnian Wan, Qi Li, Gongfan Fang +2

National University of Singapore

Diffusion Language ModelsMultimodal Diffusion Models
AskPDF
Feb 22, 2026

MultiDiffSense: Diffusion-Based Multi-Modal Visuo-Tactile Image Generation Conditioned on Object Shape and Contact Pose

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning. We present MultiDiffSense, a unified diffusion model that synthesises images for multiple vision-based tactile sensors (ViTac, TacTip, ViTacTip) within a single architecture. Our approach uses dual conditioning on CAD-derived, pose-aligned depth maps and structured prompts that encode sensor type and 4-DoF contact pose, enabling controllable, physically consistent multi-modal synthesis. Evaluating on 8 objects (5 seen, 3 novel) and unseen poses, MultiDiffSense outperforms a Pix2Pix cGAN baseline in SSIM by +36.3% (ViTac), +134.6% (ViTacTip), and +64.7% (TacTip). For downstream 3-DoF pose estimation, mixing 50% synthetic with 50% real halves the required real data while maintaining competitive performance. MultiDiffSense alleviates the data-collection bottleneck in tactile sensing and enables scalable, controllable multi-modal dataset generation for robotic applications.

Sirine Bhouri, Lan Wei, Jian-Qing Zheng +1

the Department of Bioengineering, Imperial-X Initiative, Imperial College London, London, United Kingdom. · CAMS-Oxford Institute, University of Oxford, Oxford, United Kingdom.

Synthetic Data Generation for RoboticsMultimodal Diffusion ModelsVision-Based Tactile Sensing
AskPDF
Feb 19, 2026

Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment

Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from images. However, existing image-conditioned systems suffer from two fundamental limitations: (i) they are typically trained on natural photographs, limiting their ability to capture the richer semantic, stylistic, and cultural content of artworks; and (ii) most rely on an image-to-text conversion stage, using language as a semantic shortcut that simplifies conditioning but prevents direct visual-to-audio learning. Motivated by these gaps, we introduce ArtSound, a large-scale multimodal dataset of 105,884 artwork-music pairs enriched with dual-modality captions, obtained by extending ArtGraph and the Free Music Archive. We further propose ArtToMus, the first framework explicitly designed for direct artwork-to-music generation, which maps digitized artworks to music without image-to-text translation or language-based semantic supervision. The framework projects visual embeddings into the conditioning space of a latent diffusion model, enabling music synthesis guided solely by visual information. Experimental results show that ArtToMus generates musically coherent and stylistically consistent outputs that reflect salient visual cues of the source artworks. While absolute alignment scores remain lower than those of text-conditioned systems-as expected given the substantially increased difficulty of removing linguistic supervision-ArtToMus achieves competitive perceptual quality and meaningful cross-modal correspondence. This work establishes direct visual-to-music generation as a distinct and challenging research direction, and provides resources that support applications in multimedia art, cultural heritage, and AI-assisted creative practice. Code and dataset will be publicly released upon acceptance.

Ivan Rinaldi, Matteo Mendula, Nicola Fanelli +4

University of Bari Aldo Moro, Bari, Italy · Catalonia’s Telecommunications Technology Centre, Barcelona, Spain · University of Picardie Jules Verne, Amiens, France +1

Video-to-Music GenerationMusic GenerationMultimodal Diffusion Models
AskPDF
Feb 16, 2026

Efficient Text-Guided Convolutional Adapter for the Diffusion Model

We introduce the Nexus Adapters, novel text-guided efficient adapters to the diffusion-based framework for the Structure Preserving Conditional Generation (SPCG). Recently, structure-preserving methods have achieved promising results in conditional image generation by using a base model for prompt conditioning and an adapter for structure input, such as sketches or depth maps. These approaches are highly inefficient and sometimes require equal parameters in the adapter compared to the base architecture. It is not always possible to train the model since the diffusion model is itself costly, and doubling the parameter is highly inefficient. In these approaches, the adapter is not aware of the input prompt; therefore, it is optimal only for the structural input but not for the input prompt. To overcome the above challenges, we proposed two efficient adapters, Nexus Prime and Slim, which are guided by prompts and structural inputs. Each Nexus Block incorporates cross-attention mechanisms to enable rich multimodal conditioning. Therefore, the proposed adapter has a better understanding of the input prompt while preserving the structure. We conducted extensive experiments on the proposed models and demonstrated that the Nexus Prime adapter significantly enhances performance, requiring only 8M additional parameters compared to the baseline, T2I-Adapter. Furthermore, we also introduced a lightweight Nexus Slim adapter with 18M fewer parameters than the T2I-Adapter, which still achieved state-of-the-art results. Code: https://github.com/arya-domain/Nexus-Adapters

Aryan Das, Koushik Biswas, Swalpa Kumar Roy +2

VIT Bhopal · IIIT Delhi · Tezpur University Assam +1

Diffusion Model AdaptationConditional Image GenerationT2I Diffusion ModelsMultimodal Diffusion ModelsParameter-Efficient Fine-TuningDiffusion Model Fine-Tuning
AskPDF
Feb 15, 2026

LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.

Shufan Li, Yuchen Zhu, Jiuxiang Gu +6

1Adobe · 2UCLA · 3Georgia Tech

Unified Multimodal ModelsMultimodal ReasoningMultimodal GenerationRL for Diffusion ModelsDiffusion Language ModelsMultimodal Diffusion Models+1
AskPDF
Feb 6, 2026

DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters

While generative modeling facilitates probabilistic time series forecasting, incorporating heterogeneous exogenous information remains challenging. Diffusion Transformers (DiT) provide a scalable framework for conditional generation, yet their adaptation to forecasting calls for conditioning mechanisms tailored to time series. Endogenous targets and exogenous covariates differ in sources, semantics, and statistical characteristics, while sharing temporal coordinates that support fine-grained conditional guidance. Covariates can describe future variability and temporal dependence beyond the conditional mean targeted by direct regression. Motivated by these considerations, we propose Diffusion Transformers for Time Series (DiTS), a Multimodal Diffusion Transformer for covariate-aware forecasting. DiTS models endogenous targets and exogenous covariates as distinct modalities, jointly conditioning future generation on target history and available covariates. Flow matching makes covariate-dependent distributional information relevant to velocity prediction conditioned on noisy future states. We introduce Time-aligned Modulation, extending AdaLN with the temporal-alignment prior to generate patch-wise modulation parameters from aligned covariates and diffusion time. Across diverse covariate-aware forecasting tasks, DiTS achieves strong performance in both deterministic and probabilistic forecasting, demonstrating the effectiveness of conditional generation for both point and distributional forecasting.

Haoran Zhang, Haixuan Liu, Yong Liu +4

School of Software, BNRist, Tsinghua University

Exogenous Time Series ForecastingTime Series ForecastingTime Series Forecasting with CovariatesProbabilistic Time Series ForecastingDiffusion TransformerMultimodal Diffusion Models
AskPDF
Feb 5, 2026

DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters.

Xukun Li, Yu Sun, Lei Zhang +10

XYZ Embodied AI, Beijing, China · Beijing Academy of Artificial Intelligence, Beijing, China · School of Computation, Information and Technology, Technical University of Munich, Garching, Germany +3

Bimanual Robotic ManipulationContact-Rich Robotic ManipulationTactile Sensing for Robotic ManipulationMultimodal Diffusion Models
AskPDF
Jan 5, 2026

TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers

Recent breakthroughs of transformer-based diffusion models, particularly with Multimodal Diffusion Transformers (MMDiT) driven models like FLUX and Qwen Image, have facilitated thrilling experiences in visual generation. However, these models rely only on the interactions between textual conditions and visual features to produce semantically aligned images. Once the interactions fail to reflect the nuanced compositional structure of the prompt, the generated images might be unsatisfactory. Thus, a comprehensive understanding of how different blocks and their interactions with textual conditions is crucial for better understanding the intrinsic attributes and for enhancing their interactions accordingly to strengthen the prompts adherence. In this paper, we first develop a systematic pipeline to comprehensively investigate each block's functionality by removing, disabling, and enhancing textual hidden-states at corresponding blocks. Our analysis reveals that 1) semantic information appears in earlier blocks and finer details are rendered in later blocks, 2) removing specific blocks is usually less disruptive than disabling text conditions, and 3) enhancing textual conditions in selective blocks improves semantic attributes. Building on these observations, we propose \method, a novel inference-time method for tailoring block-wise textual guidance. Our approach not only improves text-image alignment but also enables a range of downstream applications, including precise editing and inference acceleration. Extensive experiments demonstrated that our method outperforms various baselines and remains flexible across text-to-image generation, image editing, and inference acceleration. Our method improves T2I-Combench from 56.92% to 63.00% and GenEval from 66.42% to 71.63% on SD3.5, without sacrificing synthesis quality.

Binglei Li, Mengping Yang, Zhiyu Tan +2

Fudan University, Shanghai 200433, China · Shanghai Academy of AI for Science, Shanghai 200030, China · Shanghai Innovation Institute, Shanghai 200030, China

Diffusion TransformerCompositional T2I GenerationDiffusion-Based Image EditingT2I Diffusion ModelsInference-Time GuidanceMultimodal Diffusion Models
AskPDF
Dec 16, 2025

Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, their inference speed remains suboptimal due to the need to repeatedly process redundant masked tokens at every sampling step. In this work, we propose Sparse-LaViDa, a novel modeling framework that dynamically truncates unnecessary masked tokens at each inference step to accelerate MDM sampling. To preserve generation quality, we introduce specialized register tokens that serve as compact representations for the truncated tokens. Furthermore, to ensure consistency between training and inference, we design a specialized attention mask that faithfully matches the truncated sampling procedure during training. Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks including text-to-image generation, image editing, and mathematical reasoning, while maintaining generation quality.

Shufan Li, Jiuxiang Gu, Kangning Liu +4

Adobe · UCLA

Masked Diffusion ModelsDiffusion Language Model InferenceToken PruningDiffusion Model Inference AccelerationDiffusion ModelsMultimodal Diffusion Models
AskPDF
Dec 9, 2025

UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation

Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements that seamlessly blend with a given background image. The variety of real-world applications makes it highly challenging to develop a single model capable of unifying the diverse range of input-constrained generation sub-tasks, such as those conditioned by element types, sizes, or their relationships. Current methods either address only a subset of these tasks or necessitate separate model parameters for different conditions, failing to offer a truly unified solution. In this paper, we propose UniLayDiff: a Unified Diffusion Transformer, that for the first time, addresses various content-aware layout generation tasks with a single, end-to-end trainable model. Specifically, we treat layout constraints as a distinct modality and employ Multi-Modal Diffusion Transformer framework to capture the complex interplay between the background image, layout elements, and diverse constraints. Moreover, we integrate relation constraints through fine-tuning the model with LoRA after pretraining the model on other tasks. Such a schema not only achieves unified conditional generation but also enhances overall layout quality. Extensive experiments demonstrate that UniLayDiff achieves state-of-the-art performance across from unconditional to various conditional generation tasks and, to the best of our knowledge, is the first model to unify the full range of content-aware layout generation tasks.

Zeyang Liu, Le Wang, Sanping Zhou +4

College of Artificial Intelligence, Xi’an Jiaotong University · Amazon.com, Inc. · Pixocial Technology

Diffusion TransformerConditional Generative ModelingMultimodal Diffusion Models
AskPDF
Nov 4, 2025

HAGI++: Head-Assisted Gaze Imputation and Generation

Mobile eye-tracking is crucial for capturing human visual attention in real-world and XR settings, supporting research and human-computer interaction. Yet blinks, pupil-detection errors and lighting changes create missing values that hinder gaze analysis. We present HAGI++, a multi-modal diffusion-based imputation method that, for the first time, leverages integrated head-orientation sensors to exploit the natural correlation between head and eye movements. Using a transformer-based diffusion model, it learns cross-modal dependencies between eye and head data and can additionally incorporate wrist/hand motion when such wearable signals are available. Evaluations on the large-scale Nymeria, Ego-Exo4D and HOT3D datasets show that HAGI++ consistently outperforms traditional interpolation and deep-learning time-series imputation baselines. Statistical analysis confirms that its gaze-velocity distributions closely match real human behaviour, yielding realistic imputations. Even when 100% of gaze data are missing (pure gaze generation), HAGI++ exceeds methods that rely on the visual inputs and the methods rely on full-body motion capture by incorporating wrist motion from commercial wearables. Our approach enables more complete, accurate eye-gaze recordings in real-world contexts, enhancing gaze-based analysis and interaction across many applications. Our code is available at https://git.cai.simtech.uni-stuttgart.de/public-projects/HAGI

Chuhan Jiao, Zhiming Hu, Andreas Bulling

University of Stuttgart, Germany · The Hong Kong University of Science and Technology (Guangzhou), China

Gaze EstimationTime Series ImputationIncomplete Data ImputationEye TrackingMultimodal Sensor FusionMultimodal Diffusion Models
AskPDF
Oct 9, 2025

UniVideo: Unified Understanding, Generation, and Editing for Videos

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design preserves the MLLM's original text generation capabilities, enables accurate interpretation of complex multimodal instructions, and maintains visual consistency in the generated content. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as changing the environment or altering materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we released our model and code.

Cong Wei, Quande Liu, Zixuan Ye +5

University of Waterloo · Kling Team, Kuaishou Technology

Video GenerationUnified Multimodal ModelsVideo EditingImage-to-Video GenerationMultimodal Diffusion ModelsInstruction-Based Video Editing+1
AskPDF
Sep 23, 2025

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support simple image-level understanding tasks and low-resolution image generation, Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution (1024px) text-to-image synthesis. Lavida-O incorporates a novel Elastic Mixture-of-Transformers (Elastic-MoT) architecture that couples a lightweight generation branch with a larger understanding branch, supported by token compression, universal text conditioning and stratified sampling for efficient and high-quality generation. Lavida-O further incorporates planning and iterative self-reflection in image generation and editing tasks, seamlessly boosting generation quality with its understanding capabilities. Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing, outperforming existing autoregressive models and continuous diffusion models such as Qwen2.5-VL and FluxKontext-dev, while offering considerable speedup at inference. These advances establish Lavida-O as a new paradigm for scalable multimodal reasoning and generation.

Shufan Li, Jiuxiang Gu, Kangning Liu +4

Adobe · UCLA

Masked Diffusion ModelsUnified Multimodal ModelsMultimodal Foundation ModelsDiffusion-Based Image EditingT2I Diffusion ModelsDiffusion Models+2
AskPDF
Jul 8, 2025

ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion

Multimodal emotion and intent recognition is essential for automated human-computer interaction, It aims to analyze users' speech, text, and visual information to predict their emotions or intent. One of the significant challenges is that missing modalities due to sensor malfunctions or incomplete data. Traditional methods that attempt to reconstruct missing information often suffer from over-coupling and imprecise generation processes, leading to suboptimal outcomes. To address these issues, we introduce an Attention-based Diffusion model for Missing Modalities feature Completion (ADMC). Our framework independently trains feature extraction networks for each modality, preserving their unique characteristics and avoiding over-coupling. The Attention-based Diffusion Network (ADN) generates missing modality features that closely align with authentic multimodal distribution, enhancing performance across all missing-modality scenarios. Moreover, ADN's cross-modal generation offers improved recognition even in full-modality contexts. Our approach achieves state-of-the-art results on the IEMOCAP and MIntRec benchmarks, demonstrating its effectiveness in both missing and complete modality scenarios.

Yuhan Li, Wei Zhang, Juan Chen +3

National University of Defense Technology · The Fifth Electronic Research Institute of MIIT · University of Chinese Academy of Sciences +2

Cross-Modal LearningMissing-Modality LearningMultimodal Emotion RecognitionMultimodal Intent RecognitionMultimodal Diffusion Models
AskPDF
Jun 27, 2025

Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees. In this paper, we propose the Federated Multimodal Knowledge Graph Completion (FedMKGC) task, aiming at training over federated MKGs for better predicting the missing links in clients without sharing sensitive knowledge. We propose a framework named MMFeD3-HidE for addressing multimodal uncertain unavailability and multimodal client heterogeneity challenges of FedMKGC. (1) Inside the clients, our proposed Hyper-modal Imputation Diffusion Embedding model (HidE) recovers the complete multimodal distributions from incomplete entity embeddings constrained by available modalities. (2) Among clients, our proposed Multimodal FeDerated Dual Distillation (MMFeD3) transfers knowledge mutually between clients and the server with logit and feature distillation to improve both global convergence and semantic consistency. We propose a FedMKGC benchmark for a comprehensive evaluation, consisting of a general FedMKGC backbone named MMFedE, datasets with heterogeneous multimodal information, and three groups of constructed baselines. Experiments conducted on our benchmark validate the effectiveness, semantic consistency, and convergence robustness of MMFeD3-HidE.

Ying Zhang, Yu Zhao, Xuhui Sui +5

College of Computer Science, VCIP, DISSec, Nankai University, Tianjin, China · School of Software, Tiangong University, Tianjin, China · Shenzhen Campus of Sun Yat-sen University, Shenzhen, China +1

Multimodal Federated LearningMissing-Modality LearningFederated Graph LearningMultimodal KGsKG CompletionHeterogeneous Federated Learning+1
AskPDF
Jun 10, 2025

HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation

To address key limitations in human-object interaction (HOI) video generation -- specifically the reliance on curated motion data, limited generalization to novel objects/scenarios, and restricted accessibility -- we introduce HunyuanVideo-HOMA, a weakly conditioned multimodal-driven framework. HunyuanVideo-HOMA enhances controllability and reduces dependency on precise inputs through sparse, decoupled motion guidance. It encodes appearance and motion signals into the dual input space of a multimodal diffusion transformer (MMDiT), fusing them within a shared context space to synthesize temporally consistent and physically plausible interactions. To optimize training, we integrate a parameter-space HOI adapter initialized from pretrained MMDiT weights, preserving prior knowledge while enabling efficient adaptation, and a facial cross-attention adapter for anatomically accurate audio-driven lip synchronization. Extensive experiments confirm state-of-the-art performance in interaction naturalness and generalization under weak supervision. Finally, HunyuanVideo-HOMA demonstrates versatility in text-conditioned generation and interactive object manipulation, supported by a user-friendly demo interface. The project page is at https://https://bone-11.github.io/homa-page//.

Ziyao Huang, Zixiang Zhou, Juan Cao +9

University of Chinese Academy of Sciences · Tencent Hunyuan

HOI GenerationPhysical Consistency in Video GenerationControllable Video GenerationMultimodal Diffusion ModelsHuman-Object Interaction
AskPDF
May 22, 2025

LaViDa: A Large Diffusion Language Model for Multimodal Understanding

Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere to a desired format). However, existing autoregressive (AR) VLMs like LLaVA struggle in these aspects. Discrete diffusion models (DMs) offer a promising alternative, enabling parallel decoding for faster inference and bidirectional context for controllable generation through text-infilling. While effective in language-only settings, DMs' potential for multimodal tasks is underexplored. We introduce LaViDa, a family of VLMs built on DMs. We build LaViDa by equipping DMs with a vision encoder and jointly fine-tune the combined parts for multimodal instruction following. To address challenges encountered, LaViDa incorporates novel techniques such as complementary masking for effective training, prefix KV cache for efficient inference, and timestep shifting for high-quality sampling. Experiments show that LaViDa achieves competitive or superior performance to AR VLMs on multi-modal benchmarks such as MMMU, while offering unique advantages of DMs, including flexible speed-quality tradeoff, controllability, and bidirectional reasoning. On COCO captioning, LaViDa surpasses Open-LLaVa-Next-8B by +4.1 CIDEr with 1.92x speedup. On bidirectional tasks, it achieves +59% improvement on Constrained Poem Completion. These results demonstrate LaViDa as a strong alternative to AR VLMs. Code and models will be released in the camera-ready version.

Shufan Li, Konstantinos Kallidromitis, Hritik Bansal +7

1UCLA · 2Panasonic AI Research · 4Salesforce Research +1

Multimodal UnderstandingVision-Language ModelsEfficient VLM InferenceControllable Text GenerationMultimodal Foundation ModelsDiffusion Language Models+2
AskPDF
Mar 19, 2025

TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point out that textual tokens can implicitly learn visual information from vision tokens. We enhance this interaction by extracting a condensed visual representation from reference images, facilitating selective information sharing through Reference Contextual Masking -- this technique confines the usage of contextual tokens to instruction-relevant visual information. Additionally, our Winner-Takes-All module mitigates distribution shifts by prioritizing the most pertinent references for each vision token. Addressing the gap in TI2I evaluation, we also introduce the FG-TI2I Bench, a comprehensive benchmark tailored for TI2I and compatible with existing T2I methods. Our approach shows robust performance across various benchmarks, confirming its effectiveness in handling complex image-generation tasks.

Teng-Fang Hsiao, Bo-Kai Ruan, Yi-Lun Wu +2

National Yang Ming Chiao Tung University

Conditional Image GenerationCompositional T2I GenerationMultimodal Diffusion Models
AskPDF
Sep 1, 2024

Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models

The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create paragraphs or whole pages, whereby consistency and layout information are lost. To close this gap, we propose a method for imitating handwriting at the paragraph level that also works for unseen writing styles. Therefore, we introduce a modified latent diffusion model that enriches the encoder-decoder mechanism with specialized loss functions that explicitly preserve the style and content. We enhance the attention mechanism of the diffusion model with adaptive 2D positional encoding and the conditioning mechanism to work with two modalities simultaneously: a style image and the target text. This significantly improves the realism of the generated handwriting. We set a new benchmark in our comprehensive evaluation, achieving 61 % mAP and 56 % top-1 accuracy in style preservation, significantly outperforming the previous best method (37 % mAP, 30 % top-1). We are making our code publicly available for reproducibility, supporting research in this area and research into potential countermeasures: https://github.com/M4rt1nM4yr/paragraph_handwriting_imitation_ldm

Martin Mayr, Marcel Dreier, Florian Kordon +5

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany. · Planet AI GmbH, Rostock, Germany.

Latent Diffusion ModelsImage GenerationMultimodal Diffusion Models
AskPDF