Related papers: AdaState: Self-Evolving Anchors for Streaming Vide…
Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation process is an important goal moving forward and recent…
Video streaming is a fundamental Internet service, while the quality still cannot be guaranteed especially in poor network conditions such as bandwidth-constrained and remote areas. Existing works mainly work towards two directions:…
Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a single-step…
Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This…
Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models. However, these methods lack multi-view spatial-temporal modeling and encounter challenges in integrating diverse prior…
Recent Text-to-Video (T2V) models have demonstrated powerful capability in visual simulation of real-world geometry and physical laws, indicating its potential as implicit world models. Inspired by this, we explore the feasibility of…
Achieving streaming, fine-grained control over the outputs of autoregressive video diffusion models remains challenging, making it difficult to ensure that they consistently align with user expectations. To bridge this gap, we propose…
We propose FlowAnchor, a training-free framework for stable and efficient inversion-free, flow-based video editing. Inversion-free editing methods have recently shown impressive efficiency and structure preservation in images by directly…
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…
Autoregressive conditional image generation models have emerged as a dominant paradigm in text-to-image synthesis. These methods typically convert images into one-dimensional token sequences and leverage the self-attention mechanism, which…
This work demonstrates that training autoregressive video diffusion models from a single video stream$\unicode{x2013}$resembling the experience of embodied agents$\unicode{x2013}$is not only possible, but can also be as effective as…
The ultimate goal of video generation is to satisfy a fundamental trilemma: achieving high visual quality, maintaining rigorous physical consistency, and enabling precise controllability. While recent models can maintain this balance in…
Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents. In this paper, we propose a novel video prediction model, which has…
Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…
Producing prompt-faithful videos that preserve a user-specified identity remains challenging: models need to extrapolate facial dynamics from sparse reference while balancing the tension between identity preservation and motion naturalness.…
Autonomous driving requires the model to perceive the environment and (re)act within a low latency for safety. While past works ignore the inevitable changes in the environment after processing, streaming perception is proposed to jointly…
Recent video generation models largely rely on video autoencoders that compress pixel-space videos into latent representations. However, existing video autoencoders suffer from three major limitations: (1) fixed-rate compression that wastes…
We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive…
We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e.g., increasing the frame rate of the more dynamic portion of the video…