相关论文: Omni-Video: Democratizing Unified Video Understand…

We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the…

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to…

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most…

The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single…

This paper presents Omni-View, which extends the unified multimodal understanding and generation to 3D scenes based on multiview images, exploring the principle that "generation facilitates understanding". Consisting of understanding model,…

Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the…

While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective and efficient…

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural…

Unified multimodal models integrating visual understanding and generation face a fundamental challenge: visual generation incurs substantially higher computational costs than understanding, particularly for video. This imbalance motivates…

With the advancement of multi-modal Large Language Models (LLMs), Video LLMs have been further developed to perform on holistic and specialized video understanding. However, existing works are limited to specialized video understanding…

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and…

While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for…

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing…

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…

In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff , aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual…

Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos…

Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs…

Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed…