相关论文: CanvasMAR: Improving Masked Autoregressive Video P…

Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst…

Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for…

Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to…

Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in…

Generating long, high-quality videos remains a challenge due to the complex interplay of spatial and temporal dynamics and hardware limitations. In this work, we introduce MaskFlow, a unified video generation framework that combines…

Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while…

Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However,…

Stochastic video prediction models take in a sequence of image frames, and generate a sequence of consecutive future image frames. These models typically generate future frames in an autoregressive fashion, which is slow and requires the…

Classical autonomous driving systems connect perception and prediction modules via hand-crafted bounding-box interfaces, limiting information flow and propagating errors to downstream tasks. Recent research aims to develop end-to-end models…

How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. It requires learning deep and rich features with superior distinctiveness for the subtle and abstract motions. Most…

Auto-Regressive (AR) models have achieved impressive results in 2D image generation by modeling joint distributions in the grid space. While this approach has been extended to the 3D domain for powerful shape generation, it still has two…

Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video…

We reinterpret Visual Autoregressive (VAR) models as iterative refinement models to identify which design choices drive their quality-efficiency trade-off. Instead of treating VAR only as next-scale autoregression, we formalise it as a…

Autoregressive transformers have recently shown impressive image generation quality and efficiency on par with state-of-the-art diffusion models. Unlike diffusion architectures, autoregressive models can naturally incorporate arbitrary…

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities…

Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging…

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens. However,…

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works…

Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While existing methods accelerate inference by pruning tokens using frequency maps, their binary…