论文检索

Applications · Computer Vision

Zichen Miao, Zhengyuan Yang, Kevin Lin, Ze Wang, Zicheng Liu, Lijuan Wang, Qiang Qiu

Recent advancements in timestep-distilled diffusion models have enabled high-quality image generation that rivals non-distilled multi-step models, but with significantly fewer inference steps. While such models are attractive for applications due to the low inference cost and latency, fine-tuning them with a naive diffusion objective would result in degraded and blurry outputs. An intuitive alternative is to repeat the diffusion distillation process with a fine-tuned teacher model, which produces good results but is cumbersome and computationally intensive: the distillation training usually requires magnitude higher of training compute compared to fine-tuning for specific image styles. In this paper, we present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model. PSO introduces additional reference images sampled from the current time-step distilled model, and increases the relative likelihood margin between the training images and reference images. This enables the model to retain its few-step generation ability, while allowing for fine-tuning of its output distribution. We also demonstrate that PSO is a generalized formulation which be flexible extended to both offline-sampled and online-sampled pairwise data, covering various popular objectives for diffusion model preference optimization. We evaluate PSO in both preference optimization and other fine-tuning tasks, including style transfer and concept customization. We show that PSO can directly adapt distilled models to human-preferred generation with both offline and online-generated pairwise preference image data. PSO also demonstrates effectiveness in style transfer and concept customization by directly tuning timestep-distilled diffusion models.

Applications · Chemistry and Drug Discovery

Zichen Wang, Yaokun Ji, Jianing Tian, Shuangjia Zheng

Antibodies are essential proteins responsible for immune responses in organisms, capable of specifically recognizing antigen molecules of pathogens. Recent advances in generative models have significantly enhanced rational antibody design. However, existing methods mainly create antibodies from scratch without template constraints, leading to model optimization challenges and unnatural sequences. To address these issues, we propose a retrieval-augmented diffusion framework, termed RADAb, for efficient antibody design. Our method leverages a set of structural homologous motifs that align with query structural constraints to guide the generative model in inversely optimizing antibodies according to desired design criteria. Specifically, we introduce a structure-informed retrieval mechanism that integrates these exemplar motifs with the input backbone through a novel dual-branch denoising module, utilizing both structural and evolutionary information. Additionally, we develop a conditional diffusion model that iteratively refines the optimization process by incorporating both global context and local evolutionary conditions. Our approach is agnostic to the choice of generative models. Empirical experiments demonstrate that our method achieves state-of-the-art performance in multiple antibody inverse folding and optimization tasks, offering a new perspective on biomolecular generative models.

Yixuan Zhu, Haolin Wang, Ao Li, Wenliang Zhao, Yansong Tang, Jingxuan Niu, Lei Chen, Jie Zhou, Jiwen Lu

Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and computationally intensive iterative sampling. In response, we propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps. To fully exploit the potential of the pre-trained diffusion model, we devise a practical and effective diffusion distillation pipeline using dynamic noise control to address inaccuracies in updating direction during score matching. Our noise control strategy enables a dynamic diffusing scope, facilitating precise learning of denoising trajectories within the diffusion model and ensuring accurate distribution matching gradients during training. Additionally, to enrich guidance for the generative power, we incorporate textual prompts via image captioning as auxiliary conditions, fostering further exploration of the diffusion model. Extensive experiments substantiate the efficacy of our framework across a diverse array of challenging tasks and datasets, unveiling the compelling efficacy and efficiency of InstaRevive in delivering high-quality and visually appealing results.

Deep Learning · Generative Models and Autoencoders

Xin Gu, Ming Li, Libo Zhang, Fan Chen, Longyin Wen, Tiejian Luo, Sijie Zhu

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable Diffusion, DALL-E) which are not trained for image editing. Accordingly, these datasets suffer from inaccurate instruction following, poor detail preserving, and generation artifacts. In this paper, we propose to address the training data quality issue with multi-perspective reward data instead of refining the ground-truth image quality. 1) we first design a quantitative metric system based on best-in-class LVLM (Large Vision Language Model), i.e., GPT-4o in our case, to evaluate the generation quality from 3 perspectives, namely, instruction following, detail preserving, and generation quality. For each perspective, we collected quantitative score in $0\sim 5$ and text descriptive feedback on the specific failure points in ground-truth edited images, resulting in a high-quality editing reward dataset, i.e., RewardEdit20K. 2) We further proposed a novel training framework to seamlessly integrate the metric output, regarded as multi-reward, into editing models to learn from the imperfect training triplets. During training, the reward scores and text descriptions are encoded as embeddings and fed into both the latent space and the U-Net of the editing models as auxiliary conditions. During inference, we set these additional conditions to the highest score with no text description for failure points, to aim at the best generation outcome. 3) We also build a challenging evaluation benchmark with real-world images/photos and diverse editing instructions, named as Real-Edit. Experiments indicate that our multi-reward conditioned model outperforms its no-reward counterpart on two popular editing pipelines, i.e., InsPix2Pix and SmartEdit. Code is released at https://github.com/bytedance/Multi-Reward-Editing.

Deep Learning · Sequential Models, Time series

Barbora Barancikova, Zhuoyue Huang, Cristopher Salvi

Score-based diffusion models have recently emerged as state-of-the-art generativemodels for a variety of data modalities. Nonetheless, it remains unclear how toadapt these models to generate long multivariate time series. Viewing a timeseries as the discretisation of an underlying continuous process, we introduceSigDiffusion, a novel diffusion model operating on log-signature embeddingsof the data. The forward and backward processes gradually perturb and denoiselog-signatures while preserving their algebraic structure. To recover a signal fromits log-signature, we provide new closed-form inversion formulae expressing thecoefficients obtained by expanding the signal in a given basis (e.g. Fourier ororthogonal polynomials) as explicit polynomial functions of the log-signature.Finally, we show that combining SigDiffusions with these inversion formulaeresults in high-quality long time series generation, competitive with the currentstate-of-the-art on various datasets of synthetic and real-world examples.

Weifeng Lin, Xinyu Wei, Renrui Zhang, Le Zhuo, Shitian Zhao, Siyuan Huang, Junlin Xie, Gao Peng, Hongsheng Li

This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable generation, inpainting/outpainting, and more. Furthermore, we adopt Diffusion Transformers (DiT) as our foundation model and extend its capabilities with a flexible any resolution mechanism, enabling the model to dynamically process images based on the aspect ratio of the input, closely aligning with human perceptual processes. The model also incorporates structure-aware and semantic-aware guidance to facilitate effective fusion of information from the input image. Our experiments demonstrate that PixWizard not only shows impressive generative and understanding abilities for images with diverse resolutions but also exhibits generalization capabilities with unseen tasks and human instructions.

Applications · Computer Vision

Lin Zhu, Xinbing Wang, Chenghu Zhou, Qinying Gu, Nanyang Ye

Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the reference image. However, current state-of-the-art methods often struggle to disentangle content and style from style-reference images, leading to issues such as content leakages. To address this issue, we propose a masking-based method that efficiently decouples content from style without the need of tuning any model parameters. By simply masking specific elements in the style reference's image features, we uncover a critical yet under-explored principle: guiding with appropriately-selected fewer conditions (e.g., dropping several image feature elements) can efficiently avoid unwanted content flowing into the diffusion models, enhancing the style transfer performances of text-to-image diffusion models. In this paper, we validate this finding both theoretically and experimentally. Extensive experiments across various styles demonstrate the effectiveness of our masking-based method and support our theoretical results.

Deep Learning · Generative Models and Autoencoders

Xiangpeng Yang, Linchao Zhu, Hehe Fan, Yi Yang

Recent advancements in diffusion models have significantly improved video generation and editing capabilities. However, multi-grained video editing, which encompasses class-level, instance-level, and part-level modifications, remains a formidable challenge. The major difficulties in multi-grained editing include semantic misalignment of text-to-region control and feature coupling within the diffusion model. To address these difficulties, we present VideoGrain, a zero-shot approach that modulates space-time (cross- and self-) attention mechanisms to achieve fine-grained control over video content. We enhance text-to-region control by amplifying each local prompt's attention to its corresponding spatial-disentangled region while minimizing interactions with irrelevant areas in cross-attention. Additionally, we improve feature separation by increasing intra-region awareness and reducing inter-region interference in self-attention. Extensive experiments demonstrate our method achieves state-of-the-art performance in real-world scenarios. Our code, data, and demos are available on the [project page](https://knightyxp.github.io/VideoGrain_project_page/).

Applications · Computer Vision

Huaisheng Zhu, Teng Xiao, Vasant Honavar

Diffusion-based Text-to-Image (T2I) models have achieved impressive success in generating high-quality images from textual prompts. While large language models (LLMs) effectively leverage Direct Preference Optimization (DPO) for fine-tuning on human preference data without the need for reward models, diffusion models have not been extensively explored in this area. Current preference learning methods applied to T2I diffusion models immediately adapt existing techniques from LLMs. However, this direct adaptation introduces an estimated loss specific to T2I diffusion models. This estimation can potentially lead to suboptimal performance through our empirical results. In this work, we propose Direct Score Preference Optimization (DSPO), a novel algorithm that aligns the pretraining and fine-tuning objectives of diffusion models by leveraging score matching, the same objective used during pretraining. It introduces a new perspective on preference learning for diffusion models. Specifically, DSPO distills the score function of human-preferred image distributions into pretrained diffusion models, fine-tuning the model to generate outputs that align with human preferences. We theoretically show that DSPO shares the same optimization direction as reinforcement learning algorithms in diffusion models under certain conditions. Our experimental results demonstrate that DSPO outperforms preference learning baselines for T2I diffusion models in human preference evaluation tasks and enhances both visual appeal and prompt alignment of generated images.

Huaisheng Zhu, Teng Xiao, Vasant Honavar

Diffusion-based Text-to-Image (T2I) models have achieved impressive success in generating high-quality images from textual prompts. While large language models (LLMs) effectively leverage Direct Preference Optimization (DPO) for fine-tuning on human preference data without the need for reward models, diffusion models have not been extensively explored in this area. Current preference learning methods applied to T2I diffusion models immediately adapt existing techniques from LLMs. However, this direct adaptation introduces an estimated loss specific to T2I diffusion models. This estimation can potentially lead to suboptimal performance through our empirical results. In this work, we propose Direct Score Preference Optimization (DSPO), a novel algorithm that aligns the pretraining and fine-tuning objectives of diffusion models by leveraging score matching, the same objective used during pretraining. It introduces a new perspective on preference learning for diffusion models. Specifically, DSPO distills the score function of human-preferred image distributions into pretrained diffusion models, fine-tuning the model to generate outputs that align with human preferences. We theoretically show that DSPO shares the same optimization direction as reinforcement learning algorithms in diffusion models under certain conditions. Our experimental results demonstrate that DSPO outperforms preference learning baselines for T2I diffusion models in human preference evaluation tasks and enhances both visual appeal and prompt alignment of generated images.

Deep Learning · Generative Models and Autoencoders

Yichong Xia, Yimin Zhou, Jinpeng Wang, Baoyi An, Haoqian Wang, Yaowei Wang, Bin Chen

Reconstructing high-quality images under low bitrates conditions presents a challenge, and previous methods have made this task feasible by leveraging the priors of diffusion models. However, the effective exploration of pre-trained latent diffusion models and semantic information integration in image compression tasks still needs further study. To address this issue, we introduce Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement (DiffPC), a two-stage image compression framework based on stable diffusion. DiffPC efficiently encodes low-level image information, enabling the highly realistic reconstruction of the original image by leveraging high-level semantic features and the prior knowledge inherent in diffusion models. Specifically, DiffPC utilizes a multi-feature compressor to represent crucial low-level information with minimal bitrates and employs pre-embedding to acquire more robust hybrid semantics, thereby providing additional context for the decoding end. Furthermore, we have devised a control module tailored for image compression tasks, ensuring structural and textural consistency in reconstruction even at low bitrates and preventing decoding collapses induced by condition leakage. Extensive experiments demonstrate that our method achieves state-of-the-art perceptual fidelity and surpasses previous perceptual image compression methods by a significant margin in statistical fidelity.

Applications · Chemistry and Drug Discovery

Jiaqi Guan, Jiahan Li, Xiangxin Zhou, Xingang Peng, Sheng Wang, Yunan Luo, Jian Peng, Jianzhu Ma

Molecular docking is a key task in computational biology that has attracted increasing interest from the machine learning community. While existing methods have achieved success, they generally treat each protein-ligand pair in isolation. Inspired by the biochemical observation that ligands binding to the same target protein tend to adopt similar poses, we propose \textsc{GroupBind}, a novel molecular docking framework that simultaneously considers multiple ligands docking to a protein. This is achieved by introducing an interaction layer for the group of ligands and a triangle attention module for embedding protein-ligand and group-ligand pairs. By integrating our approach with diffusion based docking model, we set a new state-of-the-art performance on the PDBBind blind docking benchmark, demonstrating the effectiveness of our paradigm in enhancing molecular docking accuracy.

Deep Learning · Generative Models and Autoencoders

Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Boqing Gong, Cho-Jui Hsieh, Minhao Cheng

Diffusion models have achieved remarkable success in text-to-image generation tasks, yet the influence of initial noise remains largely unexplored. In this study, we identify specific regions within the initial noise image, termed trigger patches, that play a key role in inducing object generation in the resulting images. Notably, these patches are **universal** and can be generalized across various positions, seeds, and prompts. To be specific, extracting these patches from one noise and injecting them into another noise leads to object generation in targeted areas. To identify the trigger patches even before the image has been generated, just like consulting the crystal ball to foresee fate, we first create a dataset consisting of Gaussian noises labeled with bounding boxes corresponding to the objects appearing in the generated images and **train a detector that identifies these patches from the initial noise.** To explain the formation of these patches, we reveal that they are **outliers** in Gaussian noise, and follow distinct distributions through two-sample tests. These outliers can take effect when injected into different noises and generalize well across different settings. Finally, we find the misalignment between prompts and the trigger patch patterns can result in unsuccessful image generations. To overcome it, we propose a reject-sampling strategy to obtain optimal noise, aiming to improve prompt adherence and positional diversity in image generation.

Optimization · Sampling and Optimization

Huanjian Zhou, Baoxiang Wang, Masashi Sugiyama

In large-data applications, such as the inference process of diffusion models, it is desirable to design sampling algorithms with a high degree of parallelization. In this work, we study the adaptive complexity of sampling, which is the minimum number of sequential rounds required to achieve sampling given polynomially many queries executed in parallel at each round. For unconstrained sampling, we examine distributions that are log-smooth or log-Lipschitz and log strongly or non-strongly concave. We show that an almost linear iteration algorithm cannot return a sample with a specific exponentially small error under total variation distance. For box-constrained sampling, we show that an almost linear iteration algorithm cannot return a sample with sup-polynomially small error under total variation distance for log-concave distributions. Our proof relies upon novel analysis with the characterization of the output for the hardness potentials based on the chain-like structure with random partition and classical smoothing techniques.

Applications · Computer Vision

Jing He, Haodong Li, Wei Yin, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, YINGCONG CHEN

Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the original diffusion formulation, which may not be optimal due to the fundamental differences between dense prediction and image generation. In this paper, we provide a systemic analysis of the diffusion formulation for the dense prediction, focusing on both quality and efficiency. And we find that the original parameterization type for image generation, which learns to predict noise, is harmful for dense prediction; the multi-step noising/denoising diffusion process is also unnecessary and challenging to optimize. Based on these insights, we introduce $\textbf{Lotus}$, a diffusion-based visual foundation model with a simple yet effective adaptation protocol for dense prediction. Specifically, Lotus is trained to directly predict annotations instead of noise, thereby avoiding harmful variance. We also reformulate the diffusion process into a single-step procedure, simplifying optimization and significantly boosting inference speed. Additionally, we introduce a novel tuning strategy called detail preserver, which achieves more accurate and fine-grained predictions. Without scaling up the training data or model capacity, Lotus achieves SoTA performance in zero-shot depth and normal estimation across various datasets. It also enhances efficiency, being significantly faster than most existing diffusion-based methods. Lotus' superior quality and efficiency also enable a wide range of practical applications, such as joint estimation, single/multi-view 3D reconstruction, etc.

Deep Learning · Generative Models and Autoencoders

Wangbo Zhao, Yizeng Han, Jiasheng Tang, Kai Wang, Yibing Song, Gao Huang, Fan Wang, Yang You

Diffusion Transformer (DiT), an emerging diffusion model for image generation,has demonstrated superior performance but suffers from substantial computationalcosts. Our investigations reveal that these costs stem from the static inferenceparadigm, which inevitably introduces redundant computation in certain diffusiontimesteps and spatial regions. To address this inefficiency, we propose DynamicDiffusion Transformer (DyDiT), an architecture that dynamically adjusts its compu-tation along both timestep and spatial dimensions during generation. Specifically,we introduce a Timestep-wise Dynamic Width (TDW) approach that adapts modelwidth conditioned on the generation timesteps. In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessaryspatial locations. Extensive experiments on various datasets and different-sizedmodels verify the superiority of DyDiT. Notably, with <3% additional fine-tuning it-erations, our method reduces the FLOPs of DiT-XL by 51%, accelerates generationby 1.73×, and achieves a competitive FID score of 2.07 on ImageNet.

Deep Learning · Generative Models and Autoencoders

Yitong Deng, Winnie Lin, Lingxiao Li, Dmitriy Smirnov, Ryan Burgert, Ning Yu, Vincent Dedun, Mohammad Taghavi

Adapting pretrained image-based diffusion models to generate temporally consistent videos has become an impactful generative modeling research direction. Training-free noise-space manipulation has proven to be an effective technique, where the challenge is to preserve the Gaussian white noise distribution while adding in temporal consistency. Recently, Chang et al. (2024) formulated this problem using an integral noise representation with distribution-preserving guarantees, and proposed an upsampling-based algorithm to compute it. However, while their mathematical formulation is advantageous, the algorithm incurs a high computational cost. Through analyzing the limiting-case behavior of their algorithm as the upsampling resolution goes to infinity, we develop an alternative algorithm that, by gathering increments of multiple Brownian bridges, achieves their infinite-resolution accuracy while simultaneously reducing the computational cost by orders of magnitude. We prove and experimentally validate our theoretical claims, and demonstrate our method's effectiveness in real-world applications. We further show that our method can readily extend to the 3-dimensional space.

Deep Learning · Generative Models and Autoencoders

Haowei Lin, Shanda Li, Haotian Ye, Yiming Yang, Stefano Ermon, Yitao Liang, Jianzhu Ma

Given an unconditional generative model and a predictor for a target property (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. As a highly efficient technique for steering generative models toward flexible outcomes, training-free guidance has gained increasing attention in diffusion models. However, existing methods only handle data in continuous spaces, while many scientific applications involve both continuous and discrete data (referred to as multimodality). Another emerging trend is the growing use of the simple and general flow matching framework in building generative foundation models, where guided generation remains under-explored. To address this, we introduce TFG-Flow, a novel training-free guidance method for multimodal generative flow. TFG-Flow addresses the curse-of-dimensionality while maintaining the property of unbiased sampling in guiding discrete variables. We validate TFG-Flow on four molecular design tasks and show that TFG-Flow has great potential in drug design by generating molecules with desired properties.

Deep Learning · Generative Models and Autoencoders

Jing Wang, Ao Ma, Jiasong Feng, Dawei Leng, Yuhui Yin, Xiaodan Liang

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity. To address this redundancy, we propose the Proxy-Tokenized Diffusion Transformer (PT-DiT), which employs sparse representative token attention (where the number of representative tokens is much smaller than the total number of tokens) to efficiently model global visual information. Specifically, within each transformer block, we compute an averaging token from each spatial-temporal window to serve as a proxy token for that region. The global semantics are captured through the self-attention of these proxy tokens and then injected into all latent tokens via cross-attention. Simultaneously, we introduce window and shift window attention to address the limitations in detail modeling caused by the sparse attention mechanism. Building on the well-designed PT-DiT, we further develop the PT-T2I/V family, which includes a variety of models for T2I, T2V, and T2MV tasks. Experimental results show that PT-DiT achieves competitive performance while reducing computational complexity in image and video generation tasks (e.g., a reduction 59\% compared to DiT and a reduction 34\% compared to PixArt-$\alpha$). The visual exhibition of and code are available at https://360cvgroup.github.io/Qihoo-T2X/.

Deep Learning · Generative Models and Autoencoders

Xirui Li, Charles Herrmann, Kelvin Chan, Yinxiao Li, Deqing Sun, Chao Ma, Ming-Hsuan Yang

Recent progress in image generation has sparked research into controlling these models through condition signals, with various methods addressing specific challenges in conditional generation. Instead of proposing another specialized technique, we introduce a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation. By learning a joint distribution over a correlated image pair (e.g. image and depth) with a diffusion model, our approach enables versatile capabilities via different inference-time sampling schemes, including controllable image generation (e.g. depth to image), estimation (e.g. image to depth), signal guidance, joint generation (image \& depth), and coarse control. Previous attempts at unification often introduce complexity through multi-stage training, architectural modification, or increased parameter counts. In contrast, our simplified formulation requires a single, computationally efficient training stage, maintains the standard model input, and adds minimal learned parameters (15% of the base model). Moreover, our model supports additional capabilities like non-spatially aligned and coarse conditioning. Extensive results show that our single model can produce comparable results with specialized methods and better results than prior unified methods. We also demonstrate that multiple models can be effectively combined for multi-signal conditional generation.