相关论文: LoViC: Efficient Long Video Generation with Contex…
Long-context video modeling is essential for enabling generative models to function as world simulators, as they must maintain temporal coherence over extended time spans. However, most existing models are trained on short clips, limiting…
Diffusion Transformers (DiTs) have recently driven significant progress in text-to-video (T2V) generation. However, generating multiple videos with consistent characters and backgrounds remains a significant challenge. Existing methods…
We present TempoMaster, a novel framework that formulates long video generation as next-frame-rate prediction. Specifically, we first generate a low-frame-rate clip that serves as a coarse blueprint of the entire video sequence, and then…
Large language models, trained on extensive corpora, successfully unify diverse linguistic tasks within a single generative framework. Inspired by this, recent works like Large Vision Model (LVM) extend this paradigm to vision by organizing…
Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires controlling the generative process using highly compact conditioning signals. In this work,…
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…
Text-to-video (T2V) generation has gained significant attention due to its wide applications to video generation, editing, enhancement and translation, \etc. However, high-quality (HQ) video synthesis is extremely challenging because of the…
We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…
State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors,…
Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos…
Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without…
In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…
While diffusion model for audio-driven avatar video generation have achieved notable process in synthesizing long sequences with natural audio-visual synchronization and identity consistency, the generation of music-performance videos with…
Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-video diversity. Recent methods improve diversity for image…
Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a…
Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…
Latent variable generative models have emerged as powerful tools for generative tasks including image and video synthesis. These models are enabled by pretrained autoencoders that map high resolution data into a compressed lower dimensional…
Recent advances in learned video compression (LVC) have led to significant performance gains, with codecs such as DCVC-RT surpassing the H.266/VVC low-delay mode in compression efficiency. However, existing LVCs still exhibit key…
Diffusion models have achieved remarkable progress in video generation, but their controllability remains a major limitation. Key scene factors such as layout, lighting, and camera trajectory are often entangled or only weakly modeled,…
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and…