论文检索

Applications · Computer Vision

Yunlong Yuan, Yuanfan Guo, Chunwei Wang, Wei Zhang, Hang Xu, Li Zhang

Text-driven video generation has advanced significantly due to developments in diffusion models. Beyond the training and sampling phases, recent studies have investigated noise priors of diffusion models, as improved noise priors yield better generation results. One recent approach employs the Fourier transform to manipulate noise, marking the initial exploration of frequency operations in this context. However, it often generates videos that lack motion dynamics and imaging details. In this work, we provide a comprehensive theoretical analysis of the variance decay issue present in existing methods, contributing to the loss of details and motion dynamics. Recognizing the critical impact of noise distribution on generation quality, we introduce FreqPrior, a novel noise initialization strategy that refines noise in the frequency domain. Our method features a novel filtering technique designed to address different frequency signals while maintaining the noise prior distribution that closely approximates a standard Gaussian distribution. Additionally, we propose a partial sampling process by perturbing the latent at an intermediate timestep while finding the noise prior, significantly reducing inference time without compromising quality. Extensive experiments on VBench demonstrate that our method achieves the highest scores in both quality and semantic assessments, resulting in the best overall total score. These results highlight the superiority of our proposed noise prior.

Deep Learning · Generative Models and Autoencoders

Jan-Hendrik Bastek, WaiChing Sun, Dennis Kochmann

Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied data distribution are expected to adhere to specific governing equations. We present a framework that unifies generative modeling and partial differential equation fulfillment by introducing a first-principle-based loss term that enforces generated samples to fulfill the underlying physical constraints. Our approach reduces the residual error by up to two orders of magnitudes compared to previous work in a fluid flow case study and outperforms task-specific frameworks in relevant metrics for structural topology optimization. We also present numerical evidence that our extended training objective acts as a natural regularization mechanism against overfitting. Our framework is simple to implement and versatile in its applicability for imposing equality and inequality constraints as well as auxiliary optimization objectives. Code is available at https://github.com/jhbastek/PhysicsInformedDiffusionModels.

Applications · Computer Vision

Kennard Chan, Fayao Liu, Guosheng Lin, Chuan Sheng Foo, Weisi Lin

Existing methods for 3D clothed human digitalization perform well when the input image is captured in ideal conditions that assume the lack of any occlusion. However, in reality, images may often have occlusion problems such as incomplete observation of the human subject's full body, self-occlusion by the human subject, and non-frontal body pose. When given such input images, these existing methods fail to perform adequately. Thus, we propose Robust-PIFu, a pixel-aligned implicit model that capitalized on large-scale, pretrained latent diffusion models to address the challenge of digitalizing human subjects from non-ideal images that suffer from occlusions.Robust-PIfu offers four new contributions. Firstly, we propose a 'disentangling' latent diffusion model. This diffusion model, pretrained on billions of images, takes in any input image and removes external occlusions, such as inter-person occlusions, from that image. Secondly, Robust-PIFu addresses internal occlusions like self-occlusion by introducing a `penetrating' latent diffusion model. This diffusion model outputs multi-layered normal maps that by-pass occlusions caused by the human subject's own limbs or other body parts (i.e. self-occlusion). Thirdly, in order to incorporate such multi-layered normal maps into a pixel-aligned implicit model, we introduce our Layered-Normals Pixel-aligned Implicit Model, which improves the structural accuracy of predicted clothed human meshes. Lastly, Robust-PIFu proposes an optional super-resolution mechanism for the multi-layered normal maps. This addresses scenarios where the input image is of low or inadequate resolution. Though not strictly related to occlusion, this is still an important subproblem. Our experiments show that Robust-PIFu outperforms current SOTA methods both qualitatively and quantitatively. Our code will be released to the public.

Applications · Computer Vision

Zhengqing Wang, Jiacheng Chen, Yasutaka Furukawa

This paper proposes a novel “auto-agglomerative” 3D fracture assembly method, PuzzleFusion++, resembling how humans solve challenging spatial puzzles. Starting from individual fragments, the approach 1) aligns and merges fragments into larger groups akin to agglomerative clustering and 2) repeats the process iteratively in completing the assembly akin to auto-regressive methods. Concretely, a diffusion model denoises the 6-DoF alignment parameters of the fragments simultaneously,and a transformer model verifies and merges pairwise alignments into larger ones, whose process repeats iteratively. Extensive experiments on the Breaking Bad dataset show that PuzzleFusion++ outperforms all other state-of-the-art techniques by significant margins across all metrics In particular by over 10% in part accuracy and 50% in Chamfer distance. We will release code and model.

Applications · Computer Vision

Jianhong Bai, Menghan Xia, Xintao WANG, Ziyang Yuan, Zuozhu Liu, Haoji Hu, Pengfei Wan, Di ZHANG

Recent advancements in video diffusion models demonstrate remarkable capabilities in simulating real-world dynamics and 3D consistency. This progress motivates us to explore the potential of these models to maintain dynamic consistency across diverse viewpoints, a feature highly sought after in applications like virtual filming. Unlike existing methods focused on multi-view generation of single objects for 4D reconstruction, our interest lies in generating open-world videos from arbitrary viewpoints, incorporating six degrees of freedom (6 DoF) camera poses.To achieve this, we propose a plug-and-play module that enhances a pre-trained text-to-video model for multi-camera video generation, ensuring consistent content across different viewpoints. Specifically, we introduce a multi-view synchronization module designed to maintain appearance and geometry consistency across these viewpoints. Given the scarcity of high-quality training data, we also propose a progressive training scheme that leverages multi-camera images and monocular videos as a supplement to Unreal Engine-rendered multi-camera videos. This comprehensive approach significantly benefits our model.Experimental results demonstrate the superiority of our proposed method over existing competitors and several baselines. Furthermore, our method enables intriguing extensions, such as re-rendering a video from multiple novel viewpoints. Project webpage: https://jianhongbai.github.io/SynCamMaster/

Deep Learning · Generative Models and Autoencoders

Yihong Luo, Xiaolong Chen, Xinghua Qu, Tianyang Hu, Jing Tang

Recently, some works have tried to combine diffusion and Generative Adversarial Networks (GANs) to alleviate the computational cost of the iterative denoising inference in Diffusion Models (DMs). However, existing works in this line suffer from either training instability and mode collapse or subpar one-step generation learning efficiency. To address these issues, we introduce YOSO, a novel generative model designed for rapid, scalable, and high-fidelity one-step image synthesis with high training stability and mode coverage. Specifically, we smooth the adversarial divergence by the denoising generator itself, performing self-cooperative learning. We show that our method can serve as a one-step generation model training from scratch with competitive performance. Moreover, we extend our YOSO to one-step text-to-image generation based on pre-trained models by several effective training techniques (i.e., latent perceptual loss and latent discriminator for efficient training along with the latent DMs; the informative prior initialization (IPI), and the quick adaption stage for fixing the flawed noise scheduler). Experimental results show that YOSO achieves the state-of-the-art one-step generation performance even with Low-Rank Adaptation (LoRA) fine-tuning.In particular, we show that the YOSO-PixArt-$\alpha$ can generate images in one step trained on 512 resolution, with the capability of adapting to 1024 resolution without extra explicit training, requiring only \textasciitilde10 A800 days for fine-tuning. Our code is available at: [https://github.com/Luo-Yihong/YOSO](https://github.com/Luo-Yihong/YOSO)

Applications · Chemistry and Drug Discovery

Tomas Geffner, Kieran Didi, Zuobai Zhang, Danny Reidenbach, Zhonglin Cao, Jason Yim, Mario Geiger, Christian Dallago, Emine Kucukbenli, Arash Vahdat 等

Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop *Proteina*, a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a tailored scalable transformer architecture with up to $5\times$ as many parameters as previous models. To meaningfully quantify performance, we introduce a new set of metrics that directly measure the distributional similarity of generated proteins with reference sets, complementing existing metrics. We further explore scaling training data to millions of synthetic protein structures and explore improved training and sampling recipes adapted to protein backbone generation. This includes fine-tuning strategies like LoRA for protein backbones, new guidance methods like classifier-free guidance and autoguidance for protein backbones, and new adjusted training objectives. Proteina achieves state-of-the-art performance on de novo protein backbone design and produces diverse and designable proteins at unprecedented length, up to 800 residues. The hierarchical conditioning offers novel control, enabling high-level secondary-structure guidance as well as low-level fold-specific generation.

Applications · Chemistry and Drug Discovery

Cong Fu, Xiner Li, Blake Olson, Heng Ji, Shuiwang Ji

Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Although language models (LMs) have excelled in natural language processing, their application in SBDD is underexplored. To bridge this gap, we introduce a method, known as Frag2Seq, to apply LMs to SBDD by generating molecules in a fragment-based manner in which fragments correspond to functional modules. We transform 3D molecules into fragment-informed sequences using $SE(3)$-equivariant molecule and fragment local frames, extracting $SE(3)$-invariant sequences that preserve geometric information of 3D fragments. Furthermore, we incorporate protein pocket embeddings obtained from a pre-trained inverse folding model into the LMs via cross-attention to capture protein-ligand interaction, enabling effective target-aware molecule generation. Benefiting from employing LMs with fragment-based generation and effective protein context encoding, our model achieves the best performance on binding vina score and chemical properties such as QED and Lipinski, which shows our model’s efficacy in generating drug-like ligands with higher binding affinity against target proteins. Moreover, our method also exhibits higher sampling efficiency compared to atom-based autoregressive and diffusion baselines with at most $\times 300$ speedup. The code will be made publicly available at https://github.com/divelab/AIRS/tree/main/OpenMI/Frag2Seq.

Deep Learning · Generative Models and Autoencoders

Kang Liao, Zongsheng Yue, Zhouxia Wang, Chen Change Loy

Although learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing methods address this issue by improving data synthesis pipelines, estimating degradation kernels, employing deep internal learning, and performing domain adaptation and regularization. Previous domain adaptation methods have sought to bridge the domain gap by learning domain-invariant knowledge in either feature or pixel space. However, these techniques often struggle to extend to low-level vision tasks within a stable and compact framework. In this paper, we show that it is possible to perform domain adaptation via the noise space using diffusion models. In particular, by leveraging the unique property of how auxiliary conditional inputs influence the multi-step denoising process, we derive a meaningful *diffusion loss* that guides the restoration model in progressively aligning both restored synthetic and real-world outputs with a target clean distribution. We refer to this method as *denoising as adaptation*. To prevent shortcuts during joint training, we present crucial strategies such as channel-shuffling layer and residual-swapping contrastive learning in the diffusion model. They implicitly blur the boundaries between conditioned synthetic and real data and prevent the reliance of the model on easily distinguishable features. Experimental results on three classical image restoration tasks, namely denoising, deblurring, and deraining, demonstrate the effectiveness of the proposed method.

Deep Learning · Generative Models and Autoencoders

Hao-Chien Hsueh, Wen-Hsiao Peng, Ching-Chun Huang

Diffusion probabilistic models have achieved remarkable success in generative tasks across diverse data types. While recent studies have explored alternative degradation processes beyond Gaussian noise, this paper bridges two key diffusion paradigms: hot diffusion, which relies entirely on noise, and cold diffusion, which uses only blurring without noise. We argue that hot diffusion fails to exploit the strong correlation between high-frequency image detail and low-frequency structures, leading to random behaviors in the early steps of generation. Conversely, while cold diffusion leverages image correlations for prediction, it neglects the role of noise (randomness) in shaping the data manifold, resulting in out-of-manifold issues and partially explaining its performance drop. To integrate both strengths, we propose Warm Diffusion, a unified Blur-Noise Mixture Diffusion Model (BNMD), to control blurring and noise jointly. Our divide-and-conquer strategy exploits the spectral dependency in images, simplifying score model estimation by disentangling the denoising and deblurring processes. We further analyze the Blur-to-Noise Ratio (BNR) using spectral analysis to investigate the trade-off between model learning dynamics and changes in the data manifold. Extensive experiments across benchmarks validate the effectiveness of our approach for image generation.

Deep Learning · Generative Models and Autoencoders

Yeongmin Kim, Kwanghyeon Lee, Minsang Park, Byeonghu Na, Il-chul Moon

Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding representation from data and to adjust the dimensionality of a latent variable $\mathbf{z}$. Meanwhile, this auxiliary structure invokes an *information split problem*; the information of each data instance $\mathbf{x}_0$ is divided into diffusion endpoint $\mathbf{x}_T$ and encoded $\mathbf{z}$ because there exist two inference paths starting from the data. The latent variable modeled by diffusion endpoint $\mathbf{x}_T$ has some disadvantages. The diffusion endpoint $\mathbf{x}_T$ is computationally expensive to obtain and inflexible in dimensionality. To address this problem, we introduce Diffusion Bridge AuteEncoders (DBAE), which enables $\mathbf{z}$-dependent endpoint $\mathbf{x}_T$ inference through a feed-forward architecture. This structure creates an information bottleneck at $\mathbf{z}$, so $\mathbf{x}_T$ becomes dependent on $\mathbf{z}$ in its generation. This results in $\mathbf{z}$ holding the full information of data. We propose an objective function for DBAE to enable both reconstruction and generative modeling, with their theoretical justification. Empirical evidence supports the effectiveness of the intended design in DBAE, which notably enhances downstream inference quality, reconstruction, and disentanglement. Additionally, DBAE generates high-fidelity samples in the unconditional generation. Our code isavailable at https://github.com/aailab-kaist/DBAE.

Applications · Computer Vision

Kaifeng Zhao, Gen Li, Siyu Tang

Text-conditioned human motion generation, which allows for user interaction through natural language, has become increasingly popular. Existing methods typically generate short, isolated motions based on a single input sentence. However, human motions are continuous and can extend over long periods, carrying rich semantics. Creating long, complex motions that precisely respond to streams of text descriptions, particularly in an online and real-time setting, remains a significant challenge. Furthermore, incorporating spatial constraints into text-conditioned motion generation presents additional challenges, as it requires aligning the motion semantics specified by text descriptions with geometric information, such as goal locations and 3D scene geometry. To address these limitations, we propose **DartC**ontrol, in short **DART**, a **D**iffusion-based **A**utoregressive motion primitive model for **R**eal-time **T**ext-driven motion **C**ontrol. Our model, DART, effectively learns a compact motion primitive space jointly conditioned on motion history and text inputs using latent diffusion models. By autoregressively generating motion primitives based on the preceding history and current text input, DART enables real-time, sequential motion generation driven by natural language descriptions. Additionally, the learned motion primitive space allows for precise spatial motion control, which we formulate either as a latent noise optimization problem or as a Markov decision process addressed through reinforcement learning. We present effective algorithms for both approaches, demonstrating our model’s versatility and superior performance in various motion synthesis tasks. Experiments show our method outperforms existing baselines in motion realism, efficiency, and controllability. Video results and code are available at https://zkf1997.github.io/DART/.

Deep Learning · Generative Models and Autoencoders

Markus Mueller, Kathrin Gruber, Dennis Fok

Score-based generative models, commonly referred to as diffusion models, have proven to be successful at generating text and image data.However, their adaptation to mixed-type tabular data remains underexplored. In this work, we propose CDTD, a Continuous Diffusion model for mixed-type Tabular Data. CDTD is based on a novel combination of score matching and score interpolation to enforce a unified continuous noise distribution for both continuous and categorical features. We explicitly acknowledge the necessity of homogenizing distinct data types by relying on model-specific loss calibration and initialization schemes. To further address the high heterogeneity in mixed-type tabular data, we introduce adaptive feature- or type-specific noise schedules. These ensure balanced generative performance across features and optimize the allocation of model capacity across features and diffusion time. Our experimental results show that CDTD consistently outperforms state-of-the-art benchmark models, captures feature correlations exceptionally well, and that heterogeneity in the noise schedule design boosts sample quality. Replication code is available at https://github.com/muellermarkus/cdtd.

Applications · Computer Vision

Gaojie Lin, Jianwen Jiang, Chao Liang, Tianyun Zhong, Jiaqi Yang, Zerong Zheng, Yanbo Zheng

Diffusion-based video generation technology has advanced significantly, catalyzing a proliferation of research in human animation. While breakthroughs have been made in driving human animation through various modalities for portraits, most of current solutions for human body animation still focus on video-driven methods, leaving audio-driven taking body generation relatively underexplored. In this paper, we introduce CyberHost, a one-stage audio-driven talking body generation framework that addresses common synthesis degradations in half-body animation, including hand integrity, identity consistency, and natural motion.CyberHost's key designs are twofold. Firstly, the Region Attention Module (RAM) maintains a set of learnable, implicit, identity-agnostic latent features and combines them with identity-specific local visual features to enhance the synthesis of critical local regions. Secondly, the Human-Prior-Guided Conditions introduce more human structural priors into the model, reducing uncertainty in generated motion patterns and thereby improving the stability of the generated videos.To our knowledge, CyberHost is the first one-stage audio-driven human diffusion model capable of zero-shot video generation for the human body. Extensive experiments demonstrate that CyberHost surpasses previous works in both quantitative and qualitative aspects. CyberHost can also be extended to video-driven and audio-video hybrid-driven scenarios, achieving similarly satisfactory results.

Applications · Computer Vision

Gaojie Lin, Jianwen Jiang, Chao Liang, Tianyun Zhong, Jiaqi Yang, Zerong Zheng, Yanbo Zheng

Diffusion-based video generation technology has advanced significantly, catalyzing a proliferation of research in human animation. While breakthroughs have been made in driving human animation through various modalities for portraits, most of current solutions for human body animation still focus on video-driven methods, leaving audio-driven taking body generation relatively underexplored. In this paper, we introduce CyberHost, a one-stage audio-driven talking body generation framework that addresses common synthesis degradations in half-body animation, including hand integrity, identity consistency, and natural motion.CyberHost's key designs are twofold. Firstly, the Region Attention Module (RAM) maintains a set of learnable, implicit, identity-agnostic latent features and combines them with identity-specific local visual features to enhance the synthesis of critical local regions. Secondly, the Human-Prior-Guided Conditions introduce more human structural priors into the model, reducing uncertainty in generated motion patterns and thereby improving the stability of the generated videos.To our knowledge, CyberHost is the first one-stage audio-driven human diffusion model capable of zero-shot video generation for the human body. Extensive experiments demonstrate that CyberHost surpasses previous works in both quantitative and qualitative aspects. CyberHost can also be extended to video-driven and audio-video hybrid-driven scenarios, achieving similarly satisfactory results.

Deep Learning · Generative Models and Autoencoders

Jun Hyeong Kim, Seonghwan Kim, Seokhyun Moon, Hyeongwoo Kim, Jeheon Woo, Woo Youn Kim

Transporting between arbitrary distributions is a fundamental goal in generative modeling.Recently proposed diffusion bridge models provide a potential solution, but they rely on a joint distribution that is difficult to obtain in practice.Furthermore, formulations based on continuous domains limit their applicability to discrete domains such as graphs.To overcome these limitations, we propose Discrete Diffusion Schrödinger Bridge Matching (DDSBM), a novel framework that utilizes continuous-time Markov chains to solve the SB problem in a high-dimensional discrete state space.Our approach extends Iterative Markovian Fitting to discrete domains, and we have proved its convergence to the SB.Furthermore, we adapt our framework for the graph transformation, and show that our design choice of underlying dynamics characterized by independent modifications of nodes and edges can be interpreted as the entropy-regularized version of optimal transport with a cost function described by the graph edit distance.To demonstrate the effectiveness of our framework, we have applied DDSBM to molecular optimization in the field of chemistry.Experimental results demonstrate that DDSBM effectively optimizes molecules' property-of-interest with minimal graph transformation, successfully retaining other features. Source code is available [here](https://github.com/junhkim1226/DDSBM).

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Weicai Yan, Wang Lin, Zirun Guo, Ye Wang, Fangming Feng, Xiaoda Yang, zehan wang, Tao Jin

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods directly optimize the parameters involved in the prompt generation process through loss backpropagation, which constrains the richness and specificity of the prompt representations. In this paper, we propose Diffusion-Driven Prompt Generator (Diff-Prompt), aiming to use the diffusion model to generate rich and fine-grained prompt information for complex downstream tasks. Specifically, our approach consists of three stages. In the first stage, we train a Mask-VAE to compress the masks into latent space. In the second stage, we leverage an improved Diffusion Transformer (DiT) to train a prompt generator in the latent space, using the masks for supervision. In the third stage, we align the denoising process of the prompt generator with the pre-trained model in the semantic space, and use the generated prompts to fine-tune the model. We conduct experiments on a complex pixel-level downstream task, referring expression comprehension, and compare our method with various parameter-efficient fine-tuning approaches. Diff-Prompt achieves a maximum improvement of 8.87 in R@1 and 14.05 in R@5 compared to the foundation model and also outperforms other state-of-the-art methods across multiple metrics. The experimental results validate the effectiveness of our approach and highlight the potential of using generative models for prompt generation. Code is available at https://github.com/Kelvin-ywc/diff-prompt.

Social Aspects · Fairness, Equity, Justice and Safety

Joonsung Jeon, Woo Jae Kim, Suhyeon Ha, Sooel Son, Sung-eui Yoon

The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as replacing a specific region with a celebrity. While existing methods for protecting images from manipulation in diffusion-based generative models have primarily focused on image-to-image and text-to-image tasks, the challenge of preventing unauthorized inpainting has been rarely addressed, often resulting in suboptimal protection performance. To mitigate inpainting abuses, we propose ADVPAINT, a novel defensive framework that generates adversarial perturbations that effectively disrupt the adversary’s inpainting tasks. ADVPAINT targets the self- and cross-attention blocks in a target diffusion inpainting model to distract semantic understanding and prompt interactions during image generation. ADVPAINT also employs a two-stage perturbation strategy, dividing the perturbation region based on an enlarged bounding box around the object, enhancing robustness across diverse masks of varying shapes and sizes. Our experimental results demonstrate that ADVPAINT’s perturbations are highly effective in disrupting the adversary’s inpainting tasks, outperforming existing methods; ADVPAINT attains over a 100-point increase in FID and substantial decreases in precision.

Applications · Computer Vision

Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Hamid Alinejad-Rokny, Xiaobo Xia 等

The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation, they often face challenges when confronted with out-of-distribution data, such as which can hardly distinguish orientation, quantity, color, structure, etc. This is primarily due to their reliance on image encoders trained to encode images into task-relevant features, which may lead them to disregard irrelevant details. Delving into the modeling capabilities of diffusion models for images naturally prompts the question: Can diffusion models serve as the eyes of large language models for image perception? In this paper, we propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. This addresses the drawbacks of previous methods that solely relied on image encoders like CLIP-ViT, thereby enhancing the model's resilience against out-of-distribution samples and reducing visual hallucinations. Importantly, this is achieved without requiring additional training modules and with fewer training parameters. We extensively evaluated DEEM on both our newly constructed RobustVQA benchmark and other well-known benchmarks, POPE and MMVP, for visual hallucination and perception. In particular, DEEM improves LMM's visual perception performance to a large extent (e.g., 4\% ↑ on RobustVQA, 6.5\% ↑ on MMVP and 12.8 \% ↑ on POPE ). Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data (10\%), and a smaller base model size. Extensive experiments demonstrate that DEEM enhances the performance of LMMs on various downstream tasks without inferior performance in the long term, including visual question answering, image captioning, and text-conditioned image synthesis.

Deep Learning · Generative Models and Autoencoders

Jiatao Gu, Yuyang Wang, Yizhe Zhang, Qihang Zhang, Dinghuai Zhang, Navdeep Jaitly, Joshua Susskind, Shuangfei Zhai

Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model’s ability to fully utilize the generation trajectory, leading to inefficiencies during training and inference. In this paper, we propose DART, a transformer-based model that unifies autoregressive (AR) and diffusion within a non-Markovian framework. DART iteratively denoises image patches spatially and spectrally using an AR model that has the same architecture as standard language models. DART does not rely on image quantization, which enables more effective image modeling while maintaining flexibility. Furthermore, DART seamlessly trains with both text and image data in a unified model. Our approach demonstrates competitive performance on class-conditioned and text-to-image generation tasks, offering a scalable, efficient alternative to traditional diffusion models. Through this unified framework, DART sets a new benchmark for scalable, high-quality image synthesis.