Related papers: AHPA: Adaptive Hierarchical Prior Alignment for Di…

The field of portrait image animation, driven by speech audio input, has experienced significant advancements in the generation of realistic and dynamic portraits. This research delves into the complexities of synchronizing facial movements…

The field of computer vision has experienced significant advancements through scalable vision encoders and multimodal pre-training frameworks. However, existing approaches often treat vision encoders and large language models (LLMs) as…

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

Self-supervised pretraining has transformed computer vision by enabling data-efficient fine-tuning, yet high-resolution training typically requires server-scale infrastructure, limiting in-domain foundation model development for many…

Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparameters. However, VAEs are known to suffer from…

Drag-based editing within pretrained diffusion model provides a precise and flexible way to manipulate foreground objects. Traditional methods optimize the input feature obtained from DDIM inversion directly, adjusting them iteratively to…

The dynamical variational autoencoders (DVAEs) are a family of latent-variable deep generative models that extends the VAE to model a sequence of observed data and a corresponding sequence of latent vectors. In almost all the DVAEs of the…

Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…

Aerodynamic surrogate models are increasingly used to replace repeated high-fidelity CFD evaluations in many-query design settings, but current approaches still face two important limitations: they often scale poorly to the very large…

We present a novel unified framework that concurrently tackles recognition and future prediction for human hand pose and action modeling. Previous works generally provide isolated solutions for either recognition or prediction, which not…

The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image…

REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment between the noisy hidden projections of denoising networks and…

End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training…

Recently, probabilistic predictive coding that directly models the conditional distribution of latent features across successive frames for temporal redundancy removal has yielded promising results. Existing methods using a single-scale…

This paper studies fast adaptive beamforming optimization for the signal-to-interference-plus-noise ratio balancing problem in a multiuser multiple-input single-output downlink system. Existing deep learning based approaches to predict…

Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of…