Multimodal Diffusion Models

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 110

Oct 7, 2026cs.CV

Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models

Unified multimodal diffusion large language models (dLLMs) offer a single architecture for both image generation and multimodal understanding, but their iterative decoding requires tens to hundreds of forward passes. Existing few-step distillation methods largely focus on either image generation or text generation, making it unclear how to compress a fully discrete multimodal dLLM into a single efficient student while preserving both generation and understanding. We introduce Omni-Diffusion-Distill, a unified two-stage distillation framework that retains strong generation and understanding capabilities while substantially reducing the inference cost of a unified multimodal dLLM. Omni-Diffusion-Distill aligns the distillation of both generation and understanding, for both images and text, in the discrete token space. In the first stage, the student is trained to skip decoding steps by replaying cached teacher trajectories, and in the second stage the student is refined on intermediate states along its own rollouts. We further remedy two sources of degradation in unified distillation with a pairwise collision penalty that reduces repetition under parallel text decoding, and entropy-matched guidance that prevents entropy collapse caused by fitting the sharpened teacher distribution in image generation. Omni-Diffusion-Distill achieves state-of-the-art trade-offs between decoding efficiency and generation and understanding performance for multimodal dLLMs, reducing image generation from 128 to 8 decoding steps and multimodal understanding from 512 to 64, giving 18.2x and 21.2x wall-clock speedups. Under these budgets, it scores 0.828 on GenEval and 83.0 on DPG-Bench for text-to-image generation, while reaching GPT judge scores of 20.0 on MM-Vet and 57.2 on COCO captioning (twice the teacher's 28.4 at the same steps) for multimodal understanding.

Hong Huang, Chenhongyi Yang, Junzhe Sun +3

Simon Fraser University · Meta

Diffusion Language Model Distillation Diffusion Model Inference Acceleration Multimodal Diffusion Models T2I Diffusion Models Multimodal Understanding

Oct 5, 2026cs.CV

Learning to Read the Contextual Tokens in Diffusion Transformers

Multimodal Diffusion Transformers (MM-DiTs) jointly process visual and textual representations throughout generation. These models repeatedly update the text tokens through multimodal attention, forming dynamic contextual tokens whose function is not well understood. In this work, we introduce a framework for reading this contextual space through natural-language interrogation. We train a lightweight bottleneck network that maps intermediate contextual tokens into the input space of a frozen Large Language Model (LLM), allowing the LLM to answer questions about the emerging image directly from these hidden representations. Our reader reveals that contextual tokens encode a rich, global representation of the emerging scene: generation-specific semantics, including attributes left underspecified by the prompt, are accessible surprisingly early in denoising, while increasingly fine-grained details become readable over time. Remarkably, this information remains decodable even when the MM-DiT receives an empty prompt, showing that contextual tokens accumulate substantial image-specific information from the evolving visual representation itself. We further find that generations with more readable contextual representations tend to receive higher human-preference scores. Building on these observations, we introduce Contextual Alignment, a training technique that explicitly reinforces the visual-semantic information encoded in the contextual tokens, improving generation quality and distributional coverage. Together, our results establish contextual tokens as both an interpretable view into the internal dynamics of MM-DiTs and an effective target for improving generative models.

Omer Dahary, Etai Sella, Hadar Averbuch-Elor +2

Tel Aviv University · Cornell University

Diffusion Model Alignment Diffusion Transformer Representation Probing Multimodal Diffusion Models

Oct 4, 2026cs.CV

CleanMDM: Clean Motion Diffusion Model for Multimodal Motion Cleanup

Motion capture data is rarely directly usable, as they typically exhibit missing segments, jitter, drift and contact artifacts. Traditionally, corrupted motions are cleaned by animators through the manual identification of keyframes from noisy motion, subsequent keyframe correction, and interpolation between corrected keyframes to reconstruct coherent motion. While the rise of generative motion models has made automatic cleanup feasible, most approaches operate as black box denoisers with limited controllability, making it difficult to preserve reliable segments or enforce specific user intents. Inspired by animation workflows, we present CleanMDM, a unified multimodal motion cleanup framework that formulates cleanup as masked conditional generation with plug-and-play conditions. This single model supports arbitrary combinations of noisy 3D motion, sparse 2D keyframes, sparse 3D keyframes, and text. This design enables both automatic cleanup without additional user annotation and controllable cleanup under multimodal guidance. To further improve motion realism, we incorporate the Latent Motion Quality Discriminator (LMQD) to better match kinematic distributions and reduce skating, jitter, and interpenetration artifacts, and we apply Mesh-Aware Contact Projection as a test-time optimization step to enhance contact and physical consistency. Experiments across multiple datasets demonstrate that CleanMDM consistently outperforms prior cleanup and generation baselines, and that low cost conditions (text and 2D keyframes) provide reliable controllability gains in multimodal cleanup scenarios.

Zhe Li, Shicheng Wang, Bowen Cai +1

Peking University · Light Origins · Alibaba

Masked Diffusion Models Motion Diffusion Models Multimodal Diffusion Models

Sep 30, 2026cs.CV

Gestalt: Large Multimodal Interplay Model

In this paper, we propose Gestalt, a new paradigm of large multimodal model built around multimodal interplay. Despite rapid advances, large multimodal models are reaching a bottleneck: existing approaches focus primarily on accommodating additional modalities while overlooking the distinct characteristics of each modality and the relations among them. Motivated by the multistage property of human multisensory perception, we propose a multimodal interplay pyramid that organizes multimodal modeling as a progression from modality-specific processing, through cross-modal alignment, to deeper multimodal integration. Guided by this pyramid, Gestalt adopts a unified discrete diffusion framework and an interplay-partitioned architecture, with learnable interplay tokens mediating cross-modal exchange and integration. The pyramid also structures its data organization and training strategy. Strong performance across image generation, multimodal understanding, and text-only evaluation shows that Gestalt significantly improves cross-modal integration while preserving modality-specific information, effectively harnessing the strengths of diffusion-based multimodal models and offering a promising path toward unified multimodal intelligence. Project page: https://GeWu-Lab.github.io/Gestalt.

Zequn Yang, Yu Miao, Haotian Ni +8

Gaoling School of Artificial Intelligence, Renmin University of China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Beihang University +3

Unified Multimodal Models Cross-Modal Alignment Multimodal Generation Multimodal Diffusion Models Multimodal Understanding

Sep 30, 2026cs.AI

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback during test-time compute. Instead of relying on a separate, often larger, teacher, we leverage their self-critiques as privileged information and ask a single multimodal model to act as both teacher and student with different contexts. The student only sees the vanilla question, while the teacher conditions on the privileged critique. Then training minimizes the per-state divergence between their denoising diffusion distributions over the student's own sampling trajectories. Experiments demonstrate that UniEvo-VL improves the image generation capabilities of multimodal models, while maintaining their sensitivity to additional reflection information. Specifically, we build on top of the open-source Qwen-image-2512 and observe a significant performance gain from 0.747 to 0.808 on GenEval and from 32.97 to 35.53 on GenEval2 Soft-TIFA. Moreover, attempts with more powerful external critics (e.g., GPT5.6-Luna) show that multimodal models with strong judge capabilities can anticipate a higher self-evolving ceiling. Last but not least, mixed text-rendering outcomes show that our self-improvements may not be uniform across different tasks. Our study aims to shed light on the current hot recursive self-improvement research line to enhance the user experience when using multimodal models without external supervision or guidance.

Fang Wu, Da Xing, Yanjie Huang +16

Stanford University · Johns Hopkins University · Independent Researcher +7

Unified Multimodal Models On-Policy Self-Distillation Image Generation Multimodal Diffusion Models

Sep 29, 2026cs.CV

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary objectives, including modality-specific quality, cross-modal semantic alignment, and temporal synchronization. Its effectiveness, however, depends on two quantities that change during training: where reward-driven updates should act, and how competing rewards should be combined. Existing methods tend to rely on fixed routing and reward weights, failing to track evolving model functions. To address these limitations, we propose Adaptive Reward Routing to jointly adapt update locations and reward coordination during forward-process RL (i.e., DiffusionNFT) of joint audio-video diffusion models. Our method consists of two components. (i) Cross-Modal Influence-Guided Routing (Localizing Updates): We use bidirectional cross-attention responses as an efficient proxy for evolving cross-modal influence, dynamically reweighting token-aware losses and scaling gradients across cross-modal layers without additional model interventions. (ii) Preference-Preserving Modality-Aware Reweighting (Coordinating Rewards): We preserve predefined weights as preference priors and use branch-specific reward-gradient interactions as residual corrections after warm-up. This resolves evolving conflicts without letting dominant rewards suppress weak but essential objectives. Extensive experiments demonstrate consistent improvements in modality quality, semantic consistency, and audio-video synchronization over strong RL baselines. Ablations and mechanism analyses further validate the complementary benefits of adaptive update routing and reward coordination.

Songlin Yang, Xiaotong Zhao, Jiacheng Zhang +5

Tencent Video · The University of Hong Kong

Multi-Objective Reinforcement Learning Cross-Modal Alignment RL for Diffusion Models Multimodal Diffusion Models

Sep 29, 2026cs.CV

World2Motion: Turning Video World Models into 3D Human Motion Generators

We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt. While existing 3D motion generators learn from motion datasets, their generalization is constrained by limited coverage of environments. In contrast, video world models such as Cosmos 3 offer broader environmental priors but are not designed for full-body motion generation; recovering motion from their generated videos requires costly two-stage inference. To address these, we turn Cosmos 3 into a single-stage 3D motion generator. This adaptation has two challenges: the scarcity of paired video--motion data and temporal instability in the generated motion. First, we construct a training dataset combining synthetic video--motion pairs with real videos paired with estimated 3D motion. Second, we propose a shift-decoupled noise schedule that assigns different noise levels to video and motion through shared denoising progress. This design accommodates the different denoising requirements of the two modalities, reducing motion jitter. Experiments on a multi-source interaction benchmark show that World2Motion has better motion--text alignment and scene interaction compared with the evaluated 3D motion generators. It also matches the interaction success rate of the two-stage baseline while achieving approximately 3.3

\times

faster inference. Our project page is available at https://fyantu.github.io/World2Motion/.

Fangyuan Tu, Xiangyue Zhang, Yiyi Cai +8

Japan Advanced Institute of Science and Technology · The University of Tokyo · Institute of Science Tokyo +1

Human Motion Generation Diffusion Models for Motion Generation Video World Models Multimodal Diffusion Models

Sep 29, 2026cs.RO

Trajectory-Level Mode Guidance for Controllable Diffusion-Based Multi-Robot Motion Planning

Motion planning often admits multiple feasible solutions, making multimodal generation valuable, particularly for flexible multi-robot coordination. Diffusion models naturally learn such trajectory distributions, yet incorporating coarse and partial trajectory priors without restricting generation remains challenging. Such priors indicate a desirable region of the solution space rather than a single solution, motivating conditioned generation that preserves multimodality. In this paper, we guide trajectory generation in the clean trajectory space and progressively incorporate trajectory priors with a timestep-dependent guidance strength. At each reverse diffusion step, the reconstructed clean trajectory provides a unified space for integrating planning costs and partial trajectory priors. Planning costs are incorporated through gradient-based refinement, while the partial prior is progressively injected at the corresponding noise levels with decreasing guidance strength. This guides generation toward the prior in early stages while gradually releasing the constraint to preserve the inherent multimodality of the diffusion model. The framework naturally extends to multi-robot planning by incorporating inter-robot collision costs. Experiments on single- and multi-robot planning tasks demonstrate controllable trajectory synthesis, diverse feasible solutions, and safe multi-agent coordination.

Tianyou Yu, Shengze Cai, Chao Xu

Institute of Cyber-System and Control, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China

Multi-Robot Motion Planning Trajectory Generation Diffusion-Based Planning Diffusion Guidance Safe Motion Planning Multimodal Diffusion Models

Sep 28, 2026cs.CV

BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion

Text-to-motion generation and motion-to-text captioning are two fundamental tasks in human motion modeling, both grounded in the same underlying motion-text correspondence. Existing unified approaches mostly rely on autoregressive modeling, which imposes a fixed generation order and is therefore poorly suited to the bidirectional dependencies between language and motion, allowing early prediction errors to persist as fixed context and degrade both temporal coherence and cross-modal consistency. Masked discrete diffusion, which models sequences through iterative bidirectional prediction, offers a natural remedy. We therefore propose BiMoGen (Bidirectional Motion-text Generation), a unified masked discrete diffusion framework for bidirectional motion-text modeling. To stabilize training, we design Decoupled Uni- and Cross-Modal Training, in which masked pretraining first establishes cross-modal correspondence on paired motion-text sequences, after which supervised fine-tuning specializes the model for bidirectional generation. Masked diffusion nonetheless introduces its own source of error, as the model is trained on clean ground-truth context yet encounters self-generated and potentially erroneous context at inference, with errors committed under heavily masked states propagating through subsequent steps. We further introduce Generation-Aware Self-Correction that exposes the model to its own predictions during training and applies correction passes at early sampling steps to revise unreliably committed tokens. Extensive experiments on HumanML3D and KIT-ML demonstrate competitive performance on both tasks, validating the effectiveness of the proposed two-stage training and self-correction designs. The project page is available at https://wengwanjiang.github.io/BiMoGen-Page.

Wanjiang Weng, Yongliang Wu, Xiaofeng Tan +3

Department of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China · National University of Singapore +1

Masked Diffusion Models Text-to-Motion Generation Human Motion Generation Diffusion Models for Motion Generation Multimodal Diffusion Models

Sep 23, 2026cs.CV

Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning

Image registration and fusion aim to establish spatial correspondences from misaligned multi-modal source images, and integrate complementary information. However, in real-world imaging scenarios, source images are often affected by complex and diverse degradations, such as low illumination, noise, etc., which severely hinder the effectiveness of registration and fusion. To address this issue, we propose a mutually reinforced image registration and fusion diffusion framework via degradation-aware learning, termed Diff-RF. It explores the intrinsic coupling between registration-fusion and information restoration in the degradation conditions, enabling high-quality fusion of unregistered images under complex degradation conditions. First, the intra-modal restoration module is designed to alleviate modality-specific degradations by leveraging information within each modality, thereby providing more reliable structural representations for registration and facilitating subsequent cross-modal fusion. Second, we develop a cross-modal diffusion registration and fusion module that establishes bidirectional interaction between registration and fusion. By integrating fusion-derived visual cues and correspondence-based geometric conditions into the diffusion process, the proposed framework progressively refines spatial alignment and exploits cross-modal complementary information to achieve collaborative enhancement. Rather than treating them as independent components, degradation-aware information restoration and the collaborative optimization of registration and fusion are tightly coupled, achieving overall performance improvements. Extensive experiments on multiple extended datasets demonstrate that Diff-RF achieves superior registration accuracy and fusion quality under various degraded scenarios, exhibiting strong robustness and generalization ability.

Xunpeng Yi, Zaixi Du, Qinglong Yan +3

Electronic Information School, Wuhan University, Wuhan 430072, China

Multi-Source Image Fusion Cross-Modal Image Registration Multimodal Fusion Multimodal Diffusion Models

Sep 23, 2026cs.CV

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution. Other modalities, such as 3D body motion or audio, encode narrower aspects of the same event. We find that joint multimodal diffusion transformers exhibit a corresponding asymmetry in cross-modal correspondence: companion modalities develop strong correspondences to video, but the reciprocal correspondences through which they constrain video remain substantially weaker. We express both directions as comparable correspondence distributions over video tokens and define their disagreement as the reciprocal correspondence gap. We introduce RecCAR, standing for Reciprocal Cross-modal Attention Regularization, a KL regularizer that uses the well-established video-to-modality correspondence as a fixed reference and aligns the weaker modality-to-video correspondence toward it. Across joint video-motion and video-audio generation, RecCAR improves the Human Anatomy score from 0.69 to 0.75 and reduces audio-video desynchronization from 0.804 to 0.752, while improving overall generation

Ohad Rahamim, Dvir Samuel, Idan Schwartz +1

Bar-Ilan University · NVIDIA

Video Diffusion Models Modality Imbalance Multimodal Generation Cross-Modal Attention Multimodal Diffusion Models

Sep 17, 2026cs.CV

MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving

Autonomous driving involves coupled decision-making and scene evolution under multi-mode uncertainty. To capture this coupling and uncertainty, we introduce MM-Future, a world-action model that generates multiple paired scene-action hypotheses and models bidirectional interaction within each pair. Each hypothesis is initialized from a structured action prior and an independent future scene source, which are then co-evolved through a modality-aware diffusion Transformer. To support efficient multi-mode rollout, MM-Future compresses multi-view video into planning-oriented representations, dubbed MM-Tokens. Finally, a future-conditioned proposal scorer ranks trajectory candidates by shared history context and their paired predicted future. On NAVSIM navtest, MM-Future achieves 94.0 PDMS and 91.5 EPDMS, while attaining a 32.3 HD-Score in zero-shot closed-loop evaluation on HUGSIM. Ablations show consistent improvements over both single-mode and action-only variants, validating the benefit of multi-mode joint world-action modeling.

Shuai Liu, Hechangle Gong, Hao Jiang +5

NIO · School of Computer Science and Engineering, Sun Yat-sen University · Beihang University +1

World Models for Autonomous Driving Autonomous Driving Planning Multimodal Trajectory Prediction Multimodal Diffusion Models

Sep 17, 2026cs.LG

Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning

Multimodal models increasingly think with different modalities such as images, 3D point clouds, and robot states, not just text. Yet each modality is still encoded into its own representation space, creating a modality-switching gap whenever reasoning moves from one modality to another. In this paper, we introduce Uni-LaDiR (Unified Latent Diffusion Reasoner), a framework that unifies different modalities into a shared latent space for multimodal reasoning. A unified encoder maps teacher reasoning steps from different modalities into latent thought tokens in a shared space, trained to extract the information needed for later reasoning steps and the final output. A diffusion reasoner, trained jointly with the encoder, generates these tokens at inference without teacher reasoning steps. Across eleven vision-language model (VLM) benchmarks and two vision-language-action (VLA) suites, Uni-LaDiR achieves relative gains over the strongest baselines of 7.3% on four mathematical and logical VLM benchmarks and 6.1% on RLBench manipulation tasks. Controlled comparisons show increasing gains as more teacher modalities are unified. These results suggest that unification improves multimodal reasoning by weaving it into a single thread, where the model predicts successive thoughts in a common representation space.

Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang +3

University of California, San Diego · Meta · University of Pennsylvania

Unified Multimodal Models Multimodal Reasoning VLM Reasoning Multimodal Diffusion Models

Sep 12, 2026cs.CV

Learning Interaction between Image and Layout Priors for Joint Image-Layout Generation in Design Templates

In this paper, we address the problem of graphic design template creation, which generates a background image and a layout of foreground elements over the background to form a harmonious composition from an input text. Prior work on graphic design generation mostly adopts a sequential paradigm, where design elements are generated sequentially. We argue that such a sequential scheme falls short of faithfully capturing the dependency between the background and layout (and thus the joint image-layout distribution), which limits the quality of generated design templates. To overcome this limitation, we propose a model, InterIL, which jointly generates the two modalities, background image and layout, in a single generative process. The novel design of our joint model connects the backbones of pretrained image and layout diffusion models with a learnable communication module to explicitly model bidirectional image-layout interaction. During training, the image and layout backbones are frozen to maintain and leverage the vast pretrained single-modality prior knowledge, while only the communication module is updated, so that the model can focus on learning image-layout interaction and thereby better capture the joint image-layout distribution for improved composition harmony. Our model has no design-specific inductive bias, which allows it to better preserve the original characteristics of realistic designs. We further introduce a test-time guidance strategy to enable users to impose their specific preferences on generated results. Our experiments show that, compared with prior approaches, our model can generate significantly better results in terms of image, layout and image-layout harmonization, producing outputs closer to real samples. We also demonstrate the flexibility of our model in enforcing user preferences at inference without retraining.

Shirong Yang, Bo Yang, Ying Cao

School of Information Science and Technology, ShanghaiTech University, 393 Middle Huaxia Road, Pudong New Area, Shanghai, China

Multimodal Diffusion Models

Sep 11, 2026cs.CV

Multi-Modal Controlled Coherent Motion Generation

It is natural for humans to walk and talk simultaneously. This paper tackles the challenge of replicating such natural behaviors in 3D avatar motion generation driven by concurrent multimodal inputs, such as a text description of a man walking alongside speech audio. Existing methods, constrained by the scarcity of aligned multimodal data, typically combine motions from individual modalities sequentially or through weighted sums. However, they often result in mismatched or unrealistic movements. To overcome these limitations, we propose MOCO, a novel diffusion-based framework capable of processing multiple simultaneous inputs, including speech audio, text descriptions, and trajectory data, to generate coherent and lifelike motions without requiring aligned multimodal data. Our key innovation lies in decoupling the motion generation process. During each denoising step, the diffusion model independently generates motions for each modality from the input noise and assembles the body parts according to predefined spatial rules. The resulting combined motion is then diffused and serves as the input noise for the subsequent denoising step. This iterative approach enables each modality to refine its contribution within the context of the overall motion, progressively harmonizing movements across modalities. Consequently, the generated motions become increasingly natural and fluid with each iteration, achieving coherent and synchronized behaviors. We evaluate our approach using a purpose-built multimodal benchmark. Experimental results demonstrate that MOCO outperforms existing baselines, advancing the field of multimodal motion generation for 3D avatars.

Yifei Liu, Qiong Cao, Hongwei Yi +2

South China University of Technology · Joy Future Academy · Peking University

Human Motion Generation 3D Avatar Generation Multimodal Generation Co-Speech Gesture Generation Multimodal Diffusion Models

Sep 7, 2026cs.CV

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as multimodal planners that generate discrete VoT tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM alignment, feature reconstruction, and vector-quantization losses. These objectives make the tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic alignment and provides a structured interface for interpretable and controllable generation.

Jingxiang Sun, Chao Liao, Zhengxiong Luo +6

ByteDance Seed

T2I Generation Compositional T2I Generation Vision-Language Alignment T2I Diffusion Models Multimodal Diffusion Models

Sep 3, 2026cs.AI

The Attention Triangle in Audio-Video Models

Audio-video diffusion models rely on cross-modal attention to coordinate text, sound, and visual content, yet this same mechanism can introduce subtle and systematic semantic leakage. We study these models by probing and analyzing the ``attention triangle,'' comprising the three cross-attention edges connecting the text, audio, and video streams, and examine how semantic information is routed across modalities during generation. Our analysis reveals that routing along the audio-video edge is bidirectional: audio can influence video generation, while video can influence audio generation. This edge is shaped by biases encoded in the model's parameters and emerges as a major contributor to leakage: when prompts are in tension with learned priors, cross-modal interactions may override the intended conditioning and reroute semantics toward visually canonical but incorrect outcomes. These effects suggest that semantic artifacts arise not merely from attention spreading beyond its intended target, but from structured, bias-driven interactions along specific pathways. Building on this perspective, we extract attention-derived signals that expose how semantics are distributed and grounded across modalities, and use them as a diagnostic tool to both analyze and deliberately incur leakage under controlled conditions. This enables us to probe the internal dynamics of cross-modal routing and isolate the role of individual interactions. We further leverage these signals to guide inference-time interventions that encourage more consistent cross-modal alignment. Extensive experiments support our analysis and demonstrate improved semantic grounding while preserving generation quality.

Sagi Polaczek, Noa Kraicer, Gal Metzer +4

1Tel Aviv University · 2Simon Fraser University

Audio-Video Generation Attention Control in Diffusion Models Cross-Modal Attention Audio-Visual Alignment Multimodal Diffusion Models

Sep 1, 2026cs.CV

TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models

Although pretrained joint audio-visual diffusion models offer rich control over \emph{what} to generate, they provide no explicit control over \emph{when} an utterance should occur. To address this, we study \emph{inference-time speech scheduling}, a novel task that places coupled speech and visual articulation within user-specified begin--end intervals without finetuning the backbone model. We uncover two intrinsic properties of the denoising process that enable this task. First, a timing-sensitive text-to-audio cross-attention head exposes each utterance's model-implied source span along the latent timeline. Second, the predicted clean latent already organizes coupled speech and visual articulation, allowing their temporal placement to be edited without regenerating the content. Building on these discoveries, we propose \textbf{TimeSteer}, a training-free framework that localizes each utterance's source span through \textbf{Source Span Localization} and transfers the associated audio-visual latent content from the source interval to the specified target interval through \textbf{Region-Aware Latent Remapping}. We further introduce \textbf{SpeechShift}, the first benchmark for interval-level speech scheduling in joint audio-visual generation. Experiments across two representative backbones show that TimeSteer substantially improves interval controllability over training-free baselines while maintaining competitive overall generation quality.

Chao Zhou, Yiling Chen, Qi Chu +3

Audio-Video Generation Latent Diffusion Models Multimodal Diffusion Models

Sep 1, 2026cs.CR

Differentially Private Paired Table-Image Multimodal Synthesis

Differentially private (DP) synthesis has been extensively studied for tabular and image data separately, yet many real-world datasets contain images paired with multivariate tabular records. Synthesizing such data is particularly challenging under DP, as the two modalities favor different private learning mechanisms while their dependence must also be preserved. To address this challenge, we propose DP-TabImage, a modality-specialized framework for private paired synthesis. DP-TabImage instantiates the factorization

p(x,y)=p_T(y)p_I(x\;|\;y)

using a private Probabilistic Graphical Model for the multivariate table distribution and a table-conditioned diffusion model trained with DP-SGD for the conditional image distribution. To facilitate conditional learning under clipped and noisy gradients, we further pretrain the model on private table-image prototypes, pairing privately constructed attribute-conditioned images with tabular vectors derived from the already private tabular model at no additional privacy cost. Experiments on three real-world datasets show that DP-TabImage achieves a strong balance among tabular fidelity, image fidelity, and cross-modal alignment. Our analysis further reveals that visual warm-up primarily improves marginal image fidelity, whereas aligned table-image warm-up is critical for improving cross-modal correspondence. Our source code is available in the GitHub repository, https://github.com/KaiChen9909/TabImage_Syn.

Kai Chen, Josephine Lamp, Somesh Jha +1

University of Virginia · Dexcom · University of Wisconsin-Madison

Synthetic Data Generation Cross-Modal Alignment Differential Privacy Tabular Data Synthesis Multimodal Diffusion Models

Aug 31, 2026cs.CV

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Recent video generators often omit audio or synthesize it in a separate stage, limiting reciprocal modeling of visual dynamics and acoustic events. We present DreamX-Creator 1.0, a compact native joint audio-video generation system centered on a 7B generator. Conditioned on a first frame and a text prompt, the generator jointly denoises modality-specialized audio and video streams. The streams are processed independently in the first half of the network and coupled in the latter half through Gated Cross-Modal Attention, whose token- and head-wise output gates modulate each active cross-modal attention-head output. A unified Audio-Video Data System constructs and filters temporally coherent clips, produces structured multimodal annotations, and organizes clips into capability-oriented data pools. Progressive Joint Training comprises two audio-video pre-training stages followed by High-Quality Finetuning. Audio-Video Reinforcement Learning further post-trains the generator with Modality-Aware Multimodal Feedback that routes video-, audio-, and cross-modal feedback to the corresponding streams. For high-resolution output, our Autoregressive 1-Step 2K Refinement pipeline adapts a bidirectional multi-step teacher into an autoregressive multi-step refiner and distills it into a student requiring one denoising evaluation per temporal chunk. Overall, DreamX-Creator 1.0 achieves native, synchronized audio-video generation with performance competitive with state-of-the-art open-source systems. By releasing our compact 7B generator and 2K Refiner, we seek to democratize native audio-video generation and provide an accessible foundation for future research in unified audio-video generative modeling.

Jiashu Zhu, Yanhao Zheng, Ruitian Tian +7

DreamX Team, Alibaba Group

Audio-Video Generation Video Diffusion Models Video Generation Multimodal Diffusion Models

Aug 24, 2026cs.CV

Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model

Computed tomography (CT) throughput is limited by scan time, which grows with both the number of projections acquired and the detector integration time for each projection. Reconstructing high-quality volumes from sparse-view or low-dose measurements therefore depends on using an informative prior, typically a neural network trained for one specific scan setting and retrained whenever the modality, geometry, or material changes. We investigate whether a single diffusion model trained across several imaging domains can instead serve as a reusable prior for heterogeneous CT reconstruction problems. We evaluate the proposed method using the same diffusion visual transformer model and normalized denoising strength on three datasets that differ in modality, beam geometry, material, and degradation type, spanning additively manufactured metal parts and concrete microstructure imaged with cone-bean X-ray CT and parallel-beam neutron CT respectively. The proposed method improves upon analytic reconstructions in all three cases, demonstrating transferability across the evaluated problems and providing a step toward a reusable foundation prior for heterogeneous CT reconstruction.

Haley Duba-Sullivan, Patxi Fernandez-Zelaia, Obaidullah Rahman +1

Oak Ridge National Laboratory Oak Ridge, TN, USA

Computed Tomography Diffusion Models Multimodal Diffusion Models

Aug 13, 2026cs.CV

Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers

Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffusion models. Nevertheless, their powerful generative capabilities also raise significant safety concerns, as they may generate sensitive or inappropriate content. While existing concept erasure methods aim to mitigate such risks, most require modifying model parameters, which are often architecture-specific and impractical for deployed larger models. Several tuning-free approaches face challenges when applied to advanced large-scale MM-DiTs due to their deeply embedded knowledge, broad semantic space, and context-dependent text encoders. To address these challenges, we propose to erase concepts by directly manipulating the model's internal representations. Our key insight, derived from an in-depth analysis of MM-DiT's block-wise generative roles, is that text-conditioned semantic representations are most salient in the middle blocks of MM-DiTs. Based on this, we extract representations of an unwanted concept and a desirable safe one from the middle block, construct a steering vector from their difference, and inject this single vector into consecutive early and middle blocks. By operating exclusively on the sparse text-branch tokens and leveraging the straight sampling trajectory of rectified flow, our method achieves effective concept erasure with negligible overhead and without any training. Extensive experiments across MM-DiT models demonstrate that our method achieves state-of-the-art performance in erasing diverse concepts, enables effective control over the final output, and remains robust to adversarial attacks.

Qiao Li, Xiaomeng Fu, Yuanshu Zhao +3

Institute of Information Engineering, Chinese Academy of Sciences Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences Beijing, China

Diffusion Model Unlearning Activation Steering Concept Erasure Multimodal Diffusion Models

Aug 11, 2026cs.IR

TimeRoute: Time-Aware Modality Routing and Diffusion for Multi-Modal Recommendation

Multi-modal recommenders fuse collaborative signals with item modalities such as text, images, and audio, but the usefulness of each drifts over time and at different rates. For example, chocolate purchases typically guided by textual ingredient cues can shift toward visual packaging and ambient audio around Valentine's Day. This modality time-scale mismatch gives rise to two coupled challenges: (1) users require different modality proportions across temporal contexts, and (2) less relevant modalities are more likely to introduce outdated or misleading signals into the recommender. We address both challenges within a unified diffusion-based recommender, TimeRoute. A temporal-aware modal router maps each user's aggregated behavioral features to a personalized modality distribution, replacing the globally shared fusion weights used in prior work. The diffusion-based graph reconstructor is then conditioned on the same temporal profile through Feature-wise Linear Modulation (FiLM) with dual-stream long- and short-term denoising heads, suppressing outdated modality edges before they enter the propagation graph. Experiments on TikTok, Amazon-Baby, and Amazon-Sports demonstrate consistent improvements of up to 9.8% in Recall@K, Precision@K, and NDCG@K over strong baselines across 10-seed paired tests. Code is available at https://anonymous.4open.science/r/TimeRoute.

Pengyu Zhang, Yangqin Jiang, Klim Zaporojets +2

University of Amsterdam Amsterdam, The Netherlands · University of Hong Kong Hong Kong, China · Aarhus University Aarhus, Denmark

Recommender Systems Multimodal Recommendation Multimodal Fusion Multimodal Diffusion Models

Aug 7, 2026cs.AI

Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts

Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic instrument--tissue interactions. However, existing methods lack a unified multimodal control paradigm, while direct fusion of heterogeneous visual conditions often causes anatomical distortion, instrument appearance drift, and temporally inconsistent interactions. In this work, we propose {Surg-UniWorld}, a unified surgical world model with multimodal control experts. Surg-UniWorld first constructs a {Hierarchical Surgical Anchor} from first-frame appearance and hierarchical semantic masks to preserve persistent scene identity, anatomical organization, and interaction boundaries. {Anchor-Relative Modality Experts} then interpret edge, depth, and optical-flow evidence relative to the shared anchor, capturing complementary boundary, geometric, and motion information. A {Multimodal Control Expert} further performs contribution-preserving stage-wise composition of the activated modality increments and generates control hints for the Wan2.2 video diffusion backbone. To support multimodal surgical world modeling, we further construct Cholec80-SurgWAM, a benchmark for controllable surgical video generation. Extensive experiments demonstrate that Surg-UniWorld consistently outperforms existing controllable video generation methods and surgical world-model baselines in generation quality, temporal consistency, and multimodal controllability.

Rulin Zhou, Wanhao Liu, Guoheng Ma +8

Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR 999077, China · Shenzhen Loop Area Institute, Shen Zhen 518055, China · School of Electrical and Computer Engineering, Faculty of Engineering, the University of Sydney, Sydney, NSW 2006, Australia

Controllable Video Generation Temporal Consistency in Video Generation Video World Models Multimodal Diffusion Models

Aug 6, 2026cs.CV

Vorch-Omni: Multi-Task Orchestration of Sight and Sound

Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks. Joint audio-visual generation further increases this challenge by introducing diverse conditioning and output configurations across modalities. We present Vorch-Omni, a unified multi-task framework for audio-visual synthesis based on an arbitrary-condition-to-arbitrary-output formulation. It flexibly treats video and audio signals as either conditioning inputs or generation targets. Token-level conditioning masks and task identifiers distinguish targets, source content, and references, while position types separate temporal context from independent conditions. To capture semantic and structural information, Vorch-Omni employs complementary visual conditioning pathways: a vision-language model interprets sampled frames with text instructions, and a video VAE encodes conditions into latent tokens for direct guidance. We further build a distributed data pipeline to curate diverse temporally aligned audio-visual clips, generate structured captions and metadata, and balance heterogeneous task distributions. Built on a single flow-matching diffusion transformer without task-specific architectural changes, Vorch-Omni supports over 10 tasks, including text-to-video, text-to-audio-video, image- and reference-conditioned generation, temporal extension, audio-driven generation, video transformation, and audio-visual editing. This unified framework provides a scalable foundation for general-purpose audio-visual generation and manipulation.

Vorch Team, Xiaoyu Chen, Yang Ding +25

Audio-Video Generation Unified Multimodal Models Controllable Video Generation Multimodal Diffusion Models

Aug 5, 2026cs.CV

CSGen: A Multi-Domain Curvilinear Structure Generation Model via Hierarchical Multimodal Diffusion

Curvilinear structure analysis is an important and fundamental task in multimedia. However, the controllable generation of images with precise curvilinear structure objects remains an open challenge. To address this, we propose CSGen, a hierarchical multimodal diffusion model that synthesizes high-fidelity images precisely aligned with multiple control conditions. The CSGen is built upon three key innovations: 1) We construct a multi-domain and multimodal dataset, including over 24K samples from 5 domains and 7 different types of annotations, to train the unified generation model. 2) We propose a novel hierarchical progressive control strategy that decouples topology clues from visual context by a phased signal injection, mitigating semantic drift while ensuring the topological integrity of sparse structures. 3) We design a sparsity-aware loss re-weighting mechanism to address the extreme sparsity of curvilinear structures, significantly enhancing the attention on thin and fragile structures during optimization. Extensive experiments demonstrate that CSGen generates images with superior structure accuracy and visual realism, significantly improving downstream segmentation performance while maintaining robustness across diverse prompts. Our results confirm CSGen as a scalable, data-centric paradigm for the analysis of complex curvilinear structures in diverse multimedia applications. Code and dataset are available at https://github.com/ShanZard/CSGen.

Zhe Shan, Ziming Yang, Lei Zhou +3

Hainan University Haikou, China · Guangdong Ocean University Zhanjiang, China

Image Generation Conditional Generative Modeling Controllable Image Generation Multimodal Diffusion Models

Aug 5, 2026cs.CV

Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition

Zero-shot Skeleton Action Recognition (ZSAR) remains ambiguous when unseen actions share similar skeleton joint dynamics but differ in objects or scene context. RGB provides these missing cues, yet existing multimodal methods typically maintain independent skeleton and RGB scoring branches and fuse their outputs. Without using unlabeled test data for adaptation or fusion calibration, a fixed fusion weight cannot capture class-pair-dependent modality reliability, while an adaptive rule lacks target-side feedback for deciding which branch should dominate. We bypass this weight-selection problem via the classify-by-generation paradigm, where each class is scored by how accurately a text-conditioned denoiser predicts the noise added to the skeleton feature. This formulation separates the progressively corrupted skeleton from fixed conditioning, allowing RGB and text to jointly condition a single class-scoring function rather than produce independent scores. We instantiate this idea as Multimodal Triplet Diffusion for Skeleton-Text Matching (TDSM-MM), augmenting a text-conditioned denoising Transformer with a non-diffused RGB condition token that serves as a stable visual anchor during skeleton data reconstruction. Our proposed TDSM-MM has been ablated via extensive experiments and achieved the best inductive accuracy on three of four NTU-60/120 splits and surpasses the transductive state-of-the-art on NTU-120 96/24 (i.e., 71.3% vs. 69.1%), without test-time adaptation, suggesting that diffusion-based methods can be a promising direction for zero-shot learning.

Zehao Bao, Shujun Guo, Bruce X. B. Yu

The University of Hong Kong Hong Kong SAR, China · Zhejiang University Hangzhou, China

Skeleton-Based Action Recognition Diffusion Transformer Multimodal Diffusion Models

Aug 5, 2026cs.CV

Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution

Scene text image super-resolution (STISR) aims to recover visually plausible appearance while preserving character semantics from degraded inputs. Existing STISR systems often rely on externally generated priors or separate image and text models, resulting in error propagation and costly multi-stage inference. We present DualTSR, a unified framework that formulates STISR as coupled continuous-discrete generation. Conditional flow matching restores continuous image latents, while absorbing-state discrete diffusion reconstructs text tokens. Both processes share a multimodal transformer backbone, allowing the evolving image and text states to interact throughout generation without an external OCR prior at inference. On CTR-TSR, DualTSR achieves the best FID, LPIPS, ACC, and NED among the compared methods at both X2 and X4. On an aligned RealCE subset, it obtains the best FID, ACC, and NED with competitive LPIPS. Compared with DiffTSR at X4, DualTSR improves ACC by 12.78 percentage points while reducing the parameter count from 1.23B to 203M and end-to-end latency from 13.3s to 132ms. These results establish DualTSR as an accurate and efficient method for STISR.

Axi Niu, Knag Zhang, Qingsen Yan +3

Northwestern Polytechnical University, Xi’an, China · Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea

Image Super-Resolution Diffusion Models Multimodal Diffusion Models

Aug 4, 2026cs.AI

DiffImaginE: Imagine to Verify Entity Types with Diffusion

Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence. Existing imagine-and-compare verifiers map each (span, type) pair to one predicted visual feature, compressing diverse visual realisations into a single prototype and providing a compatibility score without explicit probabilistic semantics. We introduce DiffImaginE, which formulates MNER type verification as conditional latent diffusion inference. Given span-localised visual evidence, a type-conditioned denoiser predicts noise injected into its standardised latent. The resulting denoising error provides an ELBO-consistent surrogate for type-conditional negative log-likelihood, allowing competing type hypotheses to be ranked by how well they explain the observation. DiffImaginE retains a standard multimodal encoder stack and replaces the deterministic verifier with a classifier-free-guided diffusion scorer trained using Min-SNR weighting. We directly supervise per-type diffusion scores as classification logits, learn aggregation across noise levels, and use antithetic sampling to reduce Monte Carlo comparison variance. Our analysis shows that classifier-free guidance sharpens the induced type posterior and characterises when antithetic pairing reduces variance at equal denoiser cost. Experiments on Twitter-2015 and Twitter-2017 show consistent gains over a matched deterministic ImaginE control under the same encoder, auxiliary objectives, and evaluation protocol, supported by ablations and paired significance tests.

Feng Zhang, Feiyu Han, Rongxin Yang +11

1Fuzhou University · 2Chinese Academy of Sciences · 6Fullive Innovation (Beijing) AI Technology Co., Ltd. +5

Named Entity Recognition Conditional Diffusion Models Multimodal Diffusion Models

Aug 3, 2026cs.AI

EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning

Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions. However, existing change captioning methods always follow an autoregressive decoding paradigm to generate the change description and thus an early misinterpretation of the changed object, event, or spatial relation becomes an irreversible premise for subsequent text, amplifying visual ambiguity into cascading factual errors. To address this limitation, we propose EchoChange, a multimodal discrete diffusion language model that formulates change captioning as iterative masked-token denoising rather than left-to-right generation. By repeatedly revising the entire caption while conditioning on the image pair, EchoChange can reconsider uncertain content and correct imperfect intermediate predictions. We further introduce draft-aware dual-pass training, a progressive masking curriculum, and confidence-guided remasking to align training with iterative inference. Extensive experiments on the RSCC benchmark show that EchoChange substantially outperforms both general-purpose and remote-sensing-specific baselines across lexical and semantic metrics. The EchoChange Project is at https://github.com/sundongwei/EchoChange_Project

Dongwei Sun, Bowen Yao, Yujie Zhang +3

School of Computer Science and Technology and the Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, 710049, China · School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China · State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, 100094, China

Remote Sensing Image Understanding Masked Diffusion Models Remote Sensing Image Change Captioning Remote Sensing Change Detection Diffusion Language Models Multimodal Diffusion Models