论文检索

Computer Vision · 3D Rendering & Reconstruction

Yixuan Yang, Zhen Luo, Tongsheng Ding, Junru Lu, Mingqi Gao, Jinyu Yang, Victor Sanchez, Feng Zheng

Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e.g., GPT APIs), and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a `GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17,000 scenes, covering four common room types—bedroom, living room, kitchen, and bathroom—enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation, highlighting its applicability beyond static layout generation.

Computer Vision · Image and Video Generation

Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark, Ming-Hsuan Yang

Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appearance across frames. To address this limitation, we propose IllumiCraft, an end-to-end diffusion framework accepting three complementary inputs: (1) high-dynamic-range (HDR) video maps for detailed lighting control; (2) synthetically relit frames with randomized illumination changes (optionally paired with a static background reference image) to provide appearance cues; and (3) 3D point tracks that capture precise 3D geometry information. By integrating the lighting, appearance, and geometry cues within a unified diffusion architecture, IllumiCraft generates temporally coherent videos aligned with user-defined prompts. It supports the background-conditioned and text-conditioned video relighting and provides better fidelity than existing controllable video generation methods.

Computer Vision · Image and Video Generation

Jiahuan Wang, Yuxin Chen, Jun Yu, Guangming Lu, Wenjie Pei

Adapting pretrained diffusion-based generative models for text-driven image editing with negligible tuning overhead has demonstrated remarkable potential. A classical adaptation paradigm, as followed by these methods, first infers the generative trajectory inversely for a given source image by image inversion, then performs image editing along the inferred trajectory guided by the target text prompts. However, the performance of image editing is heavily limited by the approximation errors introduced during image inversion by diffusion models, which arise from the absence of exact supervision in the intermediate generative steps. To circumvent this issue, we investigate the parameter-efficient adaptation of VQ-based generative models for image editing, and leverage their inherent characteristic that the exact intermediate quantized representations of a source image are attainable, enabling more effective supervision for precise image inversion. Specifically, we propose \emph{EditInfinity}, which adapts \emph{Infinity}, a binary-quantized generative model, for image editing. We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation, enabling precise image inversion. Furthermore, we devise a holistic smoothing strategy which allows our \emph{EditInfinity} to perform image editing with high fidelity to source images and precise semantic alignment to the text prompts. Extensive experiments on the PIE-Bench benchmark across "add", "change", and "delete" editing operations, demonstrate the superior performance of our model compared to state-of-the-art diffusion-based baselines. Code available at: \url{https://github.com/yx-chen-ust/EditInfinity}.

Applications · Robotics

Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy—forecasting both actions and their visual consequences—explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems.

Reinforcement Learning · Everything Else

Kexin ZHENG, Lauriane Teyssier, Yinan Zheng, Yu Luo, Xianyuan Zhan

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward representations (FB) and related methods have shown promise in zero-shot RL, we empirically found that their modeling lacks expressivity and that extrapolation errors caused by out-of-distribution (OOD) actions during offline learning sometimes lead to biased representations, ultimately resulting in suboptimal performance. To address these issues, we propose Behavior-REgularizEd Zero-shot RL with Expressivity enhancement (BREEZE), an upgraded FB-based framework that simultaneously enhances learning stability, policy extraction capability, and representation learning quality. BREEZE introduces behavioral regularization in zero-shot RL policy learning, transforming policy optimization into a stable in-sample learning paradigm. Additionally, BREEZE extracts the policy using a task-conditioned diffusion model, enabling the generation of high-quality and multimodal action distributions in zero-shot RL settings. Moreover, BREEZE employs expressive attention-based architectures for representation modeling to capture the complex relationships between environmental dynamics. Extensive experiments on ExORL and D4RL Kitchen demonstrate that BREEZE achieves the best or near-the-best performance while exhibiting superior robustness compared to prior offline zero-shot RL methods. The official implementation is available at: https://github.com/Whiterrrrr/BREEZE.

Applications · Robotics

Wenbo Zhang, Tianrun Hu, Hanbo Zhang, Yanyuan Qiao, Yuchu Qin, Yang Li, Jiajun Liu, Tao Kong, Lingqiao Liu, Xiao Ma

We present Chain-of-Action (CoA), a novel visuomotor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuomotor policy. Empirically, we observe that CoA outperforms representative imitation learning algorithms such as ACT and Diffusion Policy across 60 RLBench tasks and 8 real-world tasks.

Computer Vision · Vision Models & Multimodal

Shuaizheng Liu, Jianqi Ma, Lingchen Sun, Xiangtao Kong, Lei Zhang

Despite the significant progress in diffusion prior-based image restoration for real-world scenarios, most existing methods apply uniform processing to the entire image, lacking the capability to perform region-customized image restoration according to user preferences. In this work, we propose a new framework, namely InstructRestore, to perform region-adjustable image restoration following human instructions. To achieve this, we first develop a data generation engine to produce training triplets, each consisting of a high-quality image, the target region description, and the corresponding region mask. With this engine and careful data screening, we construct a comprehensive dataset comprising 536,945 triplets to support the training and evaluation of this task. We then examine how to integrate the low-quality image features under the ControlNet architecture to adjust the degree of image details enhancement. Consequently, we develop a ControlNet-like model to identify the target region and allocate different integration scales to the target and surrounding regions, enabling region-customized image restoration that aligns with user instructions. Experimental results demonstrate that our proposed InstructRestore approach enables effective human-instructed image restoration, including restoration with controllable bokeh blur effects and region-specific restoration with continuous intensity control. Our work advances the investigation of interactive image restoration and enhancement techniques. Data, code, and models are publicly available at https://github.com/shuaizhengliu/InstructRestore.git.

Computer Vision · Everything Else

Jinpei Guo, Yifei Ji, Zheng Chen, Kai Liu, Min Liu, Wang Rao, Wenbo Li, Yong Guo, Yulun Zhang

Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a one-step diffusion codec across multiple bit-rates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics. The code and models are available at https://github.com/jp-guo/OSCAR/.

Probabilistic Methods

Meshi Bashari, Roy Maor Lotan, Yonghoon Lee, Edgar Dobriban, Yaniv Romano

Conformal prediction is a framework for predictive inference with a distribution-free, finite-sample guarantee. However, it tends to provide uninformative prediction sets when calibration data are scarce. This paper introduces Synthetic-powered predictive inference (SPI), a novel framework that incorporates synthetic data---e.g., from a generative model---to improve sample efficiency. At the core of our method is a score transporter: an empirical quantile mapping that aligns nonconformity scores from trusted, real data with those from synthetic data. By carefully integrating the score transporter into the calibration process, SPI provably achieves finite-sample coverage guarantees without making any assumptions about the real and synthetic data distributions. When the score distributions are well aligned, SPI yields substantially tighter and more informative prediction sets than standard conformal prediction. Experiments on image classification---augmenting data with synthetic diffusion-model generated images---and on tabular regression demonstrate notable improvements in predictive efficiency in data-scarce settings.

Computer Vision · Image and Video Generation

Muhammad Adnan, Nithesh Kurella, Akhil Arunkumar, Prashant Nair

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make video generation computationally expensive. Static caching mitigates this by reusing features across fixed steps but fails to adapt to generation dynamics, leading to suboptimal trade-offs between speed and quality. We propose Foresight, an adaptive layer-reuse technique that reduces computational redundancy across denoising steps while preserving baseline performance. Foresight dynamically identifies and reuses DiT block outputs for all layers across steps, adapting to generation parameters such as resolution and denoising schedules to optimize efficiency. Applied to OpenSora, Latte, and CogVideoX, Foresight achieves up to 1.63x end-to-end speedup, end-to-end speedup, while maintaining video quality.

Social Aspects · Fairness, Equity, Justice and Safety

Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal, Eoin Delaney, Chris Russell

Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often replicate and amplify societal biases, particularly along demographic attributes like gender and race. In this paper, we introduce FairImagen (https://github.com/fuzihaofzh/FairImagen), a post-hoc debiasing framework that operates on prompt embeddings to mitigate such biases without retraining or modifying the underlying diffusion model. Our method integrates Fair Principal Component Analysis to project CLIP-based input embeddings into a subspace that minimizes group-specific information while preserving semantic content. We further enhance debiasing effectiveness through empirical noise injection and propose a unified cross-demographic projection method that enables simultaneous debiasing across multiple demographic attributes. Extensive experiments across gender, race, and intersectional settings demonstrate that FairImagen significantly improves fairness with a moderate trade-off in image quality and prompt fidelity. Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.

Computer Vision · Image and Video Generation

Jiang Qin, Alexandra Gomez-Villa, Senmao Li, Shiqi Yang, Yaxing Wang, Kai Wang, Joost van de Weijer

Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with \textit{fine-grained} style customization due to challenges in controlling multiple style attributes, such as color and texture. This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation, addressing the need for independently controlled style elements for the Disentangled Stylized Image Generation (DisIG) problem. Our approach leverages the \textit{Image-Prompt Additivity} property in the CLIP image embedding space to develop techniques for separating and extracting Color-Texture Embeddings (CTE) from individual color and texture reference images. To ensure that the color palette of the generated image aligns closely with the color reference, we apply a whitening and coloring transformation to enhance color consistency. Additionally, to prevent texture loss due to the signal-leak bias inherent in diffusion training, we introduce a noise term that preserves textural fidelity during the Regularized Whitening and Coloring Transformation (RegWCT). Through these methods, our Style Attributes Disentanglement approach (SADis) delivers a more precise and customizable solution for stylized image generation. Experiments on images from the WikiArt and StyleDrop datasets demonstrate that, both qualitatively and quantitatively, SADis surpasses state-of-the-art stylization methods in the DisIG task.

Computer Vision · Image and Video Generation

Tao Liu, Dafeng Zhang, Gengchen Li, Shizhuo Liu, yongqi song, Senmao Li, Shiqi Yang, Boqian Li, Kai Wang, Yaxing Wang

Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. The core challenge lies in balancing $age\ accuracy$ and $identity\ preservation$—what we refer to as the $Age\text{-}ID\ trade\text{-}off$. Most prior methods either prioritize age transformation at the expense of identity consistency or vice versa. In this work, we address this issue by proposing a $two\text{-}pass$ face aging framework, named $Cradle2Cane$, based on few-step text-to-image (T2I) diffusion models. The first pass focuses on solving $age\ accuracy$ by introducing an adaptive noise injection ($AdaNI$) mechanism. This mechanism is guided by including prompt descriptions of age and gender for the given person as the textual condition. Also, by adjusting the noise level, we can control the strength of aging while allowing more flexibility in transforming the face. However, identity preservation is weakly ensured here to facilitate stronger age transformations. In the second pass, we enhance $identity\ preservation$ while maintaining age-specific features by conditioning the model on two identity-aware embeddings ($IDEmb$): $SVR\text{-}ArcFace$ and $Rotate\text{-}CLIP$. This pass allows for denoising the transformed image from the first pass, ensuring stronger identity preservation without compromising the aging accuracy. Both passes are $jointly\ trained\ in\ an\ end\text{-}to\text{-}end\ way\$. Extensive experiments on the CelebA-HQ test dataset, evaluated through Face++ and Qwen-VL protocols, show that our $Cradle2Cane$ outperforms existing face aging methods in age accuracy and identity consistency. Additionally, $Cradle2Cane$ demonstrates superior robustness when applied to in-the-wild human face images, where prior methods often fail. This significantly broadens its applicability to more diverse and unconstrained real-world scenarios. Code is available at https://github.com/byliutao/Cradle2Cane.

General Machine Learning · Causality

Dominik Meier, Sujai Hiremath, PROMIT GHOSAL, Kyra Gan

Distinguishing cause and effect from bivariate observational data is a foundational problem in many disciplines, but challenging without additional assumptions. Additive noise models (ANMs) are widely used to enable sample-efficient bivariate causal discovery. However, conventional ANM-based methods fail when unobserved mediators corrupt the causal relationship between variables. This paper makes three key contributions: first, we rigorously characterize why standard ANM approaches break down in the presence of unmeasured mediators. Second, we demonstrate that prior solutions for hidden mediation are brittle in finite sample settings, limiting their practical utility. To address these gaps, we propose Bivariate Denoising Diffusion (BiDD) for causal discovery, a method designed to handle latent noise introduced by unmeasured mediators. Unlike prior methods that infer directionality through mean squared error loss comparisons, our approach introduces a novel independence test statistic: during the noising and denoising processes for each variable, we condition on the other variable as input and evaluate the independence of the predicted noise relative to this input. We prove asymptotic consistency of BiDD under the ANM, and conjecture that it performs well under hidden mediation. Experiments on synthetic and real-world data demonstrate consistent performance, outperforming existing methods in mediator-corrupted settings while maintaining strong performance in mediator-free settings.

Computer Vision · Classification and Understanding

Yanghao Wang, Long Chen

Although today's pretrained discriminative vision-language models (e.g., CLIP) have demonstrated strong perception abilities, such as zero-shot image classification, they also suffer from the bag-of-words problem and spurious bias. To mitigate these problems, some pioneering studies leverage powerful generative models (e.g., pretrained diffusion models) to realize generalizable image classification, dubbed Diffusion Classifier (DC). Specifically, by randomly sampling a Gaussian noise, DC utilizes the differences of denoising effects with different category conditions to classify categories. Unfortunately, an inherent and notorious weakness of existing DCs is noise instability: different random sampled noises lead to significant performance changes. To achieve stable classification performance, existing DCs always ensemble the results of hundreds of sampled noises, which significantly reduces the classification speed. To this end, we firstly explore the role of noise in DC, and conclude that: there are some ``good noises'' that can relieve the instability. Meanwhile, we argue that these good noises should meet two principles: 1) Frequency Matching: noise should destroy the specific frequency signals; 2) Spatial Matching: noise should destroy the specific spatial areas. Regarding both principles, we propose a novel Noise Optimization method to learn matching (i.e., good) noise for DCs: NoOp. For frequency matching, NoOp first optimizes a dataset-specific noise: Given a dataset and a timestep $t$, optimize one randomly initialized parameterized noise. For Spatial Matching, NoOp trains a Meta-Network that adopts an image as input and outputs image-specific noise offset. The sum of optimized noise and noise offset will be used in DC to replace random noise. Extensive ablations on various datasets demonstrated the effectiveness of NoOp. It is worth noting that our noise optimization is orthogonal to existing optimization methods (e.g., prompt tuning), our NoOP can even benefit from these methods to further boost performance.

Probabilistic Methods · Everything Else

Emile van Krieken, Pasquale Minervini, Edoardo Maria Ponti, Antonio Vergari

Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predictors assume conditional independence between the symbols they extract, thus limiting their ability to model interactions and uncertainty --- often leading to overconfident predictions and poor out-of-distribution generalisation. To overcome the limitations of the independence assumption, we introduce _neurosymbolic diffusion models_ (NeSyDMs), a new class of NeSy predictors that use discrete diffusion to model dependencies between symbols. Our approach reuses the independence assumption from NeSy predictors at each step of the diffusion process, enabling scalable learning while capturing symbol dependencies and uncertainty quantification. Across both synthetic and real-world benchmarks — including high-dimensional visual path planning and rule-based autonomous driving — NeSyDMs achieve state-of-the-art accuracy among NeSy predictors and demonstrate strong calibration.

Theory · Learning Theory

Liming Wang, Muhammad Jehanzeb Mirza, Yishu Gong, Yuan Gong, Jiaqi Zhang, Brian Tracey, Katerina Placek, Marco Vilela, Jim Glass

This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations with commonly used weak supervision such as partial labels and multiple views. Within this framework, we establish identifiability conditions for diffusion models to disentangle latent variable models with \emph{stochastic}, \emph{non-invertible} mixing processes. We also prove \emph{finite-sample global convergence} for diffusion models to disentangle independent subspace models. To validate our theory, we conduct extensive disentanglement experiments on subspace recovery in latent subspace Gaussian mixture models, image colorization, denoising, and voice conversion for speech classification. Our experiments show that training strategies inspired by our theory, such as style guidance regularization, consistently enhance disentanglement performance.

General Machine Learning · Transfer, Multitask and Meta-learning

guojun lei, Rong Zhang, Tianhang Liu, Hong Li, Zhiyuan Ma, Chi Wang, Weiwei Xu

Recent advancements in video generation models have enabled the creation of diverse and realistic videos, with promising applications in advertising and film production. However, as one of the essential tasks of video generation models, video concept transfer remains significantly challenging. Existing methods generally model video as an entirety, leading to limited flexibility and precision when solely editing specific regions or concepts. To mitigate this dilemma, we propose a novel architecture UniTransfer, which introduces both spatial and diffusion timestep decomposition in a progressive paradigm, achieving precise and controllable video concept transfer. Specifically, in terms of spatial decomposition, we decouple videos into three key components: the foreground subject, the background, and the motion flow. Building upon this decomposed formulation, we further introduce a dual-to-single-stream DiT-based architecture for supporting fine-grained control over different components in the videos. We also introduce a self-supervised pretraining strategy based on random masking to enhance the decomposed representation learning from large-scale unlabeled video data. Inspired by the Chain-of-Thought reasoning paradigm, we further revisit the denoising diffusion process and propose a Chain-of-Prompt (CoP) mechanism to achieve the timestep decomposition. We decompose the denoising process into three stages of different granularity and leverage large language models (LLMs) for stage-specific instructions to guide the generation progressively. We also curate an animal-centric video dataset called OpenAnimal to facilitate the advancement and benchmarking of research in video concept transfer. Extensive experiments demonstrate that our method achieves high-quality and controllable video concept transfer across diverse reference images and scenes, surpassing existing baselines in both visual fidelity and editability.

Theory · Learning Theory

Gen Li, Changxiao Cai

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially, diffusion models allow for parallel sampling, offering a promising path to accelerate generation and eliminate the left-to-right generation constraints. Despite their empirical success, theoretical understandings of diffusion language models remain underdeveloped. In this work, we develop convergence guarantees for diffusion language models from an information-theoretic perspective. Our analysis demonstrates that the sampling error, measured by the Kullback-Leibler (KL) divergence, decays inversely with the number of iterations $T$ and scales linearly with the mutual information between tokens in the target text sequence. Crucially, our theory covers the regime $T<L$, where $L$ is the text sequence length. This justifies that high-quality samples can be generated with fewer iterations than $L$, thereby breaking the fundamental sampling bottleneck of $L$ steps required by AR models. We further establish matching upper and lower bounds, up to some constant factor, that shows the tightness of our convergence analysis. These results offer novel theoretical insights into the practical effectiveness of diffusion language models.

Probabilistic Methods

SEOKJU HAHN, Junghye Lee

Diffusion models have demonstrated decent generation quality, yet their deployment in federated learning scenarios remains challenging. Due to data heterogeneity and a large number of parameters, conventional parameter averaging schemes often fail to achieve stable collaborative training of diffusion models. We reframe collaborative synthetic data generation as a cooperative sampling procedure from a mixture of decentralized distributions, each encoded by a pre-trained local diffusion model. This leverages the connection between diffusion and energy-based models, which readily supports compositional generation thereof. Consequently, we can directly obtain refined synthetic dataset, optionally with differential privacy guarantee, even without exchanging diffusion model parameters. Our framework reduces communication overhead while maintaining the generation quality, realized through an unadjusted Langevin algorithm with a convergence guarantee.