Related papers: ContentV: Efficient Training of Video Generation M…
Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from limited video duration and narrow evaluation scopes, making it…
Long video understanding is a complex task that requires both spatial detail and temporal awareness. While Vision-Language Models (VLMs) obtain frame-level understanding capabilities through multi-frame input, they suffer from information…
Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve…
In the dynamic field of digital content creation using generative models, state-of-the-art video editing models still do not offer the level of quality and control that users desire. Previous works on video editing either extended from…
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…
Recent advances in text-to-music generation (TTM) have yielded high-quality results, but often at the cost of extensive compute and the use of large proprietary internal data. To improve the affordability and openness of TTM training, an…
This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. The InternVid dataset contains over 7…
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…
Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes…
The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text.The previous cI2V generation methods conventionally perform in RGB pixel space, with…
In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual…
Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…
We introduce Vidu, a high-performance text-to-video generator that is capable of producing 1080p videos up to 16 seconds in a single generation. Vidu is a diffusion model with U-ViT as its backbone, which unlocks the scalability and the…
The efficacy of video generation models heavily depends on the quality of their training datasets. Most previous video generation models are trained on short video clips, while recently there has been increasing interest in training long…
Video gaming streaming services are growing rapidly due to new services such as passive video streaming, e.g. Twitch.tv, and cloud gaming, e.g. Nvidia Geforce Now. In contrast to traditional video content, gaming content has special…
We introduce an approach to generating videos based on a series of given language descriptions. Frames of the video are generated sequentially and optimized by guidance from the CLIP image-text encoder; iterating through language…
Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these…
Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the…
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…
The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality…