Related papers: SCFlow: Implicitly Learning Style and Content Dise…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or comic series colorization. Despite advancements in visual…

Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image generation or protein folding & design, and discrete, exemplified by diffusion large language…

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their…

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label…

Many real-world applications of flow-based generative models desire a diverse set of samples that cover multiple modes of the target distribution. However, the predominant approach for obtaining diverse sets is not sample-efficient, as it…

What defines a visual style? Fashion styles emerge organically from how people assemble outfits of clothing, making them difficult to pin down with a computational model. Low-level visual similarity can be too specific to detect…

Diffusion models have emerged as the leading approach for style transfer, yet they struggle with photo-realistic transfers, often producing painting-like results or missing detailed stylistic elements. Current methods inadequately address…

A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks…

Deep generative models provide state-of-the-art performance across a wide array of applications, with recent studies showing increasing applicability for science and engineering. Despite a growing corpus of literature focused on the…

We consider visual domains in which a class label specifies the content of an image, and class-irrelevant properties that differentiate instances constitute the style. We present a domain-independent method that permits the open-ended…

In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and…

Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tuning-free, often suffer from content leakage, where semantic…

The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method…

Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which estimate the average velocity between timesteps, mitigate this…