In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing video generative models apply fixed compression rates via pretrained VAE, we observe that real-world video content exhibits substantial temporal non-uniformity, with high-motion segments containing more information than static scenes. Based on this insight, DLFR-VAE dynamically adjusts the latent frame rate according to the content complexity. Specifically, DLFR-VAE comprises two core innovations: (1) A Dynamic Latent Frame Rate Scheduler that partitions videos into temporal chunks and adaptively determines optimal frame rates based on information-theoretic content complexity, and (2) A training-free adaptation mechanism that transforms pretrained VAE architectures into a dynamic VAE that can process features with variable frame rates. Our simple but effective DLFR-VAE can function as a plug-and-play module, seamlessly integrating with existing video generation models and accelerating the video generation process.
Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
Tsinghua University（清华大学）；Carnegie Mellon University（卡内基梅隆大学）；Peking University（北京大学）；CASIA；University of Electronic Science and Technology of China（电子科技大学）；Guangming Laboratory（光明实验室）
Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
Zhipu AI, Beijing, China（智谱AI，北京，中国）；Tsinghua University, Beijing, China（清华大学，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications. However, it is always a challenge to achieve the consistency between the learned latent distribution and the prior latent distribution when optimizing the evidence lower bound (ELBO), and finally leads to an unsatisfactory performance in data generation. In this paper, we propose a latent distribution consistency approach to avoid such substantial inconsistency between the posterior and prior latent distributions in ELBO optimizing. W…
We present fast, realistic image generation on high-resolution, multimodal datasets using hierarchical variational autoencoders (VAEs) trained on a deterministic autoencoder's latent space. In this two-stage setup, the autoencoder compresses the image into its semantic features, which are then modeled with a deep VAE. With this method, the VAE avoids modeling the fine-grained details that constitute the majority of the image's code length, allowing it to focus on learning its structural components. We demonstrate the effectiveness of our two-stage approach, achieving a FID of 9.34 on the Image…
On Color Alignment in VAE Latent Spaces and Its Applications
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；City University of Hong Kong (Dongguan)（香港城市大学（东莞））；Universitat de València（瓦伦西亚大学）
Nankai University（南开大学）；Agency for Science Technology and Research (A*STAR)（新加坡科技研究局）
Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen classes by transferring knowledge from semantic descriptions to visual representations. Recent generative methods formulate GZSL as a missing data problem, which mainly adopts GANs or VAEs to generate visual features for unseen classes. However, GANs often suffer from instability, and VAEs can only optimize the lower bound on the log-likelihood of observed data. To overcome the above limitations, we resort to generative flows, a family of generative models with the advantage of accurate likelihood estimation. More spe…
VAE requires the standard Gaussian distribution as a prior in the latent space. Since all codes tend to follow the same prior, it often suffers the so-called "posterior collapse". To avoid this, this paper introduces the class specific distribution for the latent code. But different from CVAE, we present a method for disentangling the latent space into the label relevant and irrelevant dimensions, $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$, for a single input. We apply two separated encoders to map the input into $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$ respectively, and then give the conc…
LDPM: Towards undersampled MRI reconstruction with MR-VAE and Latent Diffusion Prior
Shenzhen Technology University（深圳科技大学）；Shenzhen University（深圳大学）；Huawei（华为）；Nanjing University of Science and Technology（南京理工大学）；Qilu University of Technology（齐鲁工业大学）
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) the latent vector across space, concatenate fixed X- and Y-"coordinate" channels, and apply a fully convolutional network with 1x1 stride. This provides an architectural prior for dissociating positional from non-positional features in the latent distribution of VAEs, yet without providing any explicit supervision to this effect. We show that this architecture, which we …
Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of shared representations, while neglecting the important private aspects of data within individual modalities. In this paper, we introduce a disentangled multi-modal variational autoencoder (DMVAE) that utilizes disentangled VAE strategy to separate the private and shared latent spaces of multiple modalities. We specifically consider the instance where the laten…
Multiple Sclerosis (MS) and microvascular leukoencephalopathy are two distinct neurological conditions, the first caused by focal autoimmune inflammation in the central nervous system, the second caused by chronic white matter damage from atherosclerotic microvascular disease. Both conditions lead to signal anomalies on Fluid Attenuated Inversion Recovery (FLAIR) magnetic resonance (MR) images, which can be distinguished by an expert neuroradiologist, but which can look very similar to the untrained eye as well as in the early stage of both diseases. In this paper, we attempt to train a 3-dime…
Learning Enabled Components (LECs) are widely being used in a variety of perception based autonomy tasks like image segmentation, object detection, end-to-end driving, etc. These components are trained with large image datasets with multimodal factors like weather conditions, time-of-day, traffic-density, etc. The LECs learn from these factors during training, and while testing if there is variation in any of these factors, the components get confused resulting in low confidence predictions. The images with factors not seen during training is commonly referred to as Out-of-Distribution (OOD). …
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea（韩国首尔 Chung-Ang 大学人工智能系）；SNUAILAB, Seoul, Republic of Korea（韩国首尔 SNUAILAB 实验室）
Autodesk AI Research（欧特克人工智能研究院）；Imagia（Imagia公司）；MILA（蒙特利尔学习算法研究所）
The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks. There is a growing interest in the question of whether features learned on one environment will generalize across different environments. We demonstrate here that VAE latent variables often focus on some factors of variation at the expense of others - in this case we refer to the features as ``imbalanced''. Feature imbalance leads to poor generalization when the latent variables are used in an environment where the presence of features…
Samsung AI Center（三星人工智能中心）；Rutgers University（罗格斯大学）
We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor disentanglement have focused on sophisticated learning objectives within the VAE framework, their choice of a standard normal as the latent factor prior is both suboptimal and detrimental to performance. Our key observation is that the disentangled latent variables responsible for major sources of variability, the relevant factors, can be more appropriately modeled using long-tail distributions. The typical Gaussian…
University Medicine Essen（埃森大学医学院）；Graz University of Technology（格拉茨工业大学）；NVIDIA（英伟达）
The reconstruction loss and the Kullback-Leibler divergence (KLD) loss in a variational autoencoder (VAE) often play antagonistic roles, and tuning the weight of the KLD loss in $β$-VAE to achieve a balance between the two losses is a tricky and dataset-specific task. As a result, current practices in VAE training often result in a trade-off between the reconstruction fidelity and the continuity$/$disentanglement of the latent space, if the weight $β$ is not carefully tuned. In this paper, we present intuitions and a careful analysis of the antagonistic mechanism of the two losses, and propose…
Stevens Institute of Technology（史蒂文斯理工学院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
This paper proposes a joint training method to learn both the variational auto-encoder (VAE) and the latent energy-based model (EBM). The joint training of VAE and latent EBM are based on an objective function that consists of three Kullback-Leibler divergences between three joint distributions on the latent vector and the image, and the objective function is of an elegant symmetric and anti-symmetric form of divergence triangle that seamlessly integrates variational and adversarial learning. In this joint training scheme, the latent EBM serves as a critic of the generator model, while the gen…
Tsinghua University（清华大学）；UC San Diego（加州大学圣地亚哥分校）；Qualcomm, Inc.（高通公司）；University of Amsterdam（阿姆斯特丹大学）
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing signals to the latent encoding/embedding in VAE without changing its main backbone architecture, hence retaining the desirable properties of the VAE. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE. In the unsupervised strategy, we guide the VAE learning by int…
MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction
The Hong Kong University of Science and Technology（香港科技大学）；Peking University（北京大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Lightspeed Studios（光速工作室）
Samsung AI Center Cambridge（三星剑桥人工智能中心）；Rutgers University（罗格斯大学）
We deal with the problem of learning the underlying disentangled latent factors that are shared between the paired bi-modal data in cross-modal retrieval. Our assumption is that the data in both modalities are complex, structured, and high dimensional (e.g., image and text), for which the conventional deep auto-encoding latent variable models such as the Variational Autoencoder (VAE) often suffer from difficulty of accurate decoder training or realistic synthesis. A suboptimally trained decoder can potentially harm the model's capability of identifying the true factors. In this paper we propos…
Massachusetts Institute of Technology（麻省理工学院）；New York Structural Biology Center（纽约结构生物学中心）
Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose any specific structure on the learned latent representations. We propose a method for explicitly disentangling image rotation and translation from other unstructured latent factors in a variational autoencoder (VAE) framework. By formulating the generative model as a function of the spatial coordinate, we make the reconstruction error differentiable with respe…
University of Toronto（多伦多大学）；Vector Institute（向量学院）；Google Research（谷歌研究院）
We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models. Exemplar VAE is a variant of VAE with a non-parametric prior in the latent space based on a Parzen window estimator. To sample from it, one first draws a random exemplar from a training set, then stochastically transforms that exemplar into a latent code and a new observation. We propose retrieval augmented training (RAT) as a way to speed up Exemplar VAE training by using approximate nearest neighbor search in the latent space to define a lower…
Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, th…
Warsaw University of Technology（华沙理工大学）；Jagiellonian University（雅盖隆大学）；Tooploox
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophic forgetting in the same way as other neural structures. Recent generative continual learning works approach this problem and try to learn from new data without forgetting previous knowledge. However, those methods usually focus on artificial scenarios where examples share almost no similarity between subsequent portions of data - an assumption not realistic in the real-life applications of continual learning. In thi…
Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However, there is some debate about how to encourage disentanglement with VAEs and evidence indicates that existing implementations of VAEs do not achieve disentanglement consistently. The evaluation of how well a VAE's latent space has been disentangled is often evaluated against our subjective expectations of which attributes should be disentangled for a given probl…
Geometric disentanglement, the separation of latent codes for intrinsic (i.e. identity) and extrinsic(i.e. pose) geometry, is a prominent task for generative models of non-Euclidean data such as 3D deformable models. It provides greater interpretability of the latent space, and leads to more control in generation. This work introduces a mesh feature, the conformal factor and normal feature (CFAN),for use in mesh convolutional autoencoders. We further propose CFAN-VAE, a novel architecture that disentangles identity and pose using the CFAN feature. Requiring no label information on the identity…
University of Tübingen（图宾根大学）；IMPRS-IS（马克斯·普朗克智能系统研究所国际马克斯·普朗克研究学院）
Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference. The proposal of $β$-VAEs (Higgins et al., 2017) breaks this interpretation and generalizes VAEs to application domains beyond generative modeling (e.g., representation learning, clustering, or lossy data compression) by introducing an objective function that allows practitioners to trade off between the information content ("bit rate") of the latent representation and the distortion of reconstructed data (Alemi et al., 2018)…
