Related papers: SRA 2: Variational Autoencoder Self-Representation…

Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy -- representation alignment (REPA) that matches DiT hidden features to those of a non-generative teacher…

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep…

In real-world traffic surveillance, vehicle images captured under adverse weather, poor lighting, or high-speed motion often suffer from severe noise and blur. Such degradations significantly reduce the accuracy of license plate recognition…

Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and prone to shortcut learning under shifted boundary conditions. We introduce **REPA-P**, a…

Test-time adaption (TTA) has witnessed important progress in recent years, the prevailing methods typically first encode the image and the text and design strategies to model the association between them. Meanwhile, the image encoder is…

Combining neuroimaging datasets from multiple sites and scanners can help increase statistical power and thus provide greater insight into subtle neuroanatomical effects. However, site-specific effects pose a challenge by potentially…

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of…

Recently most successful image synthesis models are multi stage process to combine the advantages of different methods, which always includes a VAE-like model for faithfully reconstructing embedding to image and a prior model to generate…

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…

Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned embeddings.To generate new samples, an autoregressive prior…

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing…

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve…

Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergence and high-quality generation in latent diffusion models.…

Representation Alignment (REPA) has emerged as a simple way to accelerate Diffusion Transformers training in latent space. At the same time, pixel-space diffusion transformers such as Just image Transformers (JiT) have attracted growing…

The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on…

How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our…