Bridging Video Understanding and Generation in a Unified Framework

• URL: http://arxiv.org/abs/2606.31326v1
• Date: Tue, 30 Jun 2026 08:29:29 GMT
• Title: Bridging Video Understanding and Generation in a Unified Framework
• Abstract summary: We propose Vega, a unified framework that bridges video understanding and generation.<n>Vega employs a hybrid architecture combining autoregressive (AR) prediction with rendering.<n>Vega achieves strong performance on video generation benchmarks like VBench and video understanding benchmarks like VideoMME.
• Score: 17.354510332268273
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recently, unified image generation and understanding have been extensively explored. However, extending such unified modeling paradigms to the video domain remains largely underexplored. A central challenge is that video understanding favors compact, discriminative semantic representations, whereas video generation requires dense signals that preserve visual details and temporal coherence. Videos naturally capture both spatial semantics and temporal dynamics, making them a more suitable modality for unified multimodal modeling compared to static images. In this paper, we propose Vega, a unified framework that bridges video understanding and generation. Vega leverages a shared vocabulary to jointly model text and visual representations and employs a hybrid architecture combining autoregressive (AR) prediction with diffusion-based rendering. Specifically, the AR model focuses on predicting semantically meaningful visual tokens for keyframes, providing a structured representation that guides the diffusion module in rendering dense, high-resolution video frames. Extensive experiments demonstrate that Vega achieves strong performance on video generation benchmarks such as VBench and video understanding benchmarks like VideoMME.

Related papers

• Gen4U: Unifying Video Generation and Understanding via Diffusion [25.621217360501106]
  We show that video diffusion models evolve across both network depth and noise levels.<n>We introduce Gen4U, a framework that repurposes these generative representations with a single forward pass.<n>Experiments establish that frozen, large-scale video diffusion models function as highly competitive video encoders.
  arXiv  Detail & Related papers  (2026-07-07T23:17:26Z)
• SkyReels-V3 Technique Report [23.793804843416606]
  Video robustness serves as a cornerstone for building world models, where contextual inference stands as the defining test of capability.<n>We present SkyReels-V3, a conditional video generation model, built upon a unified multimodal in-context learning framework with diffusion Transformers.<n>SkyReels-V3 model supports three core generative paradigms within a single architecture: images-to-video synthesis, video-to-video extension and audio-guided video generation.
  arXiv  Detail & Related papers  (2026-01-24T06:08:12Z)
• BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration [56.98981194478512]
  We propose a unified framework that handles a broad range of subject-to-video scenarios.<n>We introduce an MLLM-DiT framework in which a pretrained multimodal large language model performs deep cross-modal reasoning to ground entities.<n>Experiments on the OpenS2V benchmark demonstrate that our method achieves superior performance across subject consistency, naturalness, and text relevance in generated videos.
  arXiv  Detail & Related papers  (2025-10-01T02:41:11Z)
• FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning [65.42201665046505]
  Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question.<n>This static approach limits their ability to adaptively gather visual evidence, leading to suboptimal performance on tasks that require broad temporal coverage or fine-grained spatial detail.<n>We introduce FrameMind, an end-to-end framework trained with reinforcement learning that enables models to dynamically request visual information during reasoning through Frame-Interleaved Chain-of-Thought (FiCOT)<n>Unlike traditional approaches, FrameMind operates in multiple turns where the model alternates between textual reasoning and active visual perception, using tools to extract
  arXiv  Detail & Related papers  (2025-09-28T17:59:43Z)
• StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation [117.13475564834458]
  We propose a new way of self-attention calculation, termed Consistent Self-Attention. To extend our method to long-range video generation, we introduce a novel semantic space temporal motion prediction module. By merging these two novel components, our framework, referred to as StoryDiffusion, can describe a text-based story with consistent images or videos.
  arXiv  Detail & Related papers  (2024-05-02T16:25:16Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation [73.54366331493007]
  VideoGen is a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency. We leverage an off-the-shelf text-to-image generation model, e.g., Stable Diffusion, to generate an image with high content quality from the text prompt.
  arXiv  Detail & Related papers  (2023-09-01T11:14:43Z)
• Imagen Video: High Definition Video Generation with Diffusion Models [64.06483414521222]
  Imagen Video is a text-conditional video generation system based on a cascade of video diffusion models. We find Imagen Video capable of generating videos of high fidelity, but also having a high degree of controllability and world knowledge.
  arXiv  Detail & Related papers  (2022-10-05T14:41:38Z)
• Leveraging Local Temporal Information for Multimodal Scene Classification [9.548744259567837]
  Video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. We propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames.
  arXiv  Detail & Related papers  (2021-10-26T19:58:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.