Learning World Models for Interactive Video Generation

• URL: http://arxiv.org/abs/2505.21996v1
• Date: Wed, 28 May 2025 05:55:44 GMT
• Title: Learning World Models for Interactive Video Generation
• Authors: Taiye Chen, Xun Hu, Zihan Ding, Chi Jin,
• Abstract summary: We enhance image-to-video models with interactive capabilities through additional action conditioning and autoregressive framework.<n>We propose video retrieval augmented generation (VRAG) with explicit global state conditioning, which significantly reduces long-term compounding errors.<n>Our work establishes a comprehensive benchmark for improving video generation models with internal world modeling capabilities.
• Score: 21.028685555298292
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities due to two main challenges: compounding errors and insufficient memory mechanisms. We enhance image-to-video models with interactive capabilities through additional action conditioning and autoregressive framework, and reveal that compounding error is inherently irreducible in autoregressive video generation, while insufficient memory mechanism leads to incoherence of world models. We propose video retrieval augmented generation (VRAG) with explicit global state conditioning, which significantly reduces long-term compounding errors and increases spatiotemporal consistency of world models. In contrast, naive autoregressive generation with extended context windows and retrieval-augmented generation prove less effective for video generation, primarily due to the limited in-context learning capabilities of current video models. Our work illuminates the fundamental challenges in video world models and establishes a comprehensive benchmark for improving video generation models with internal world modeling capabilities.

Related papers

• Controllable Video Generation: A Survey [72.38313362192784]
  We provide a systematic review of controllable video generation, covering both theoretical foundations and recent advances in the field.<n>We begin by introducing the key concepts and commonly used open-source video generation models.<n>We then focus on control mechanisms in video diffusion models, analyzing how different types of conditions can be incorporated into the denoising process to guide generation.
  arXiv  Detail & Related papers  (2025-07-22T06:05:34Z)
• Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis [12.160537328404622]
  textttDRA-Ctrl provides new insights into reusing resource-intensive video models.<n>textttDRA-Ctrl lays foundation for future unified generative models across visual modalities.
  arXiv  Detail & Related papers  (2025-05-29T10:34:45Z)
• Vid2World: Crafting Video Diffusion Models to Interactive World Models [38.270098691244314]
  Vid2World is a general approach for leveraging and transferring pre-trained video diffusion models into interactive world models.<n>It performs casualization of a pre-trained video diffusion model by crafting its architecture and training objective to enable autoregressive generation.<n>It introduces a causal action guidance mechanism to enhance action controllability in the resulting interactive world model.
  arXiv  Detail & Related papers  (2025-05-20T13:41:45Z)
• Learning 3D Persistent Embodied World Models [84.40585374179037]
  We introduce a new persistent embodied world model with an explicit memory of previously generated content.<n>During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent.<n>This generation is then aggregated into a persistent 3D map of the environment.
  arXiv  Detail & Related papers  (2025-05-05T17:59:17Z)
• AdaWorld: Learning Adaptable World Models with Latent Actions [76.50869178593733]
  We propose AdaWorld, an innovative world model learning approach that enables efficient adaptation.<n>Key idea is to incorporate action information during the pretraining of world models.<n>We then develop an autoregressive world model that conditions on these latent actions.
  arXiv  Detail & Related papers  (2025-03-24T17:58:15Z)
• VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models [71.9811050853964]
  VideoJAM is a novel framework that instills an effective motion prior to video generators.<n>VideoJAM achieves state-of-the-art performance in motion coherence.<n>These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.
  arXiv  Detail & Related papers  (2025-02-04T17:07:10Z)
• EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling [8.250616459360684]
  We introduce EDELINE, a unified world model architecture that integrates state space models with diffusion models.<n>Our approach outperforms existing baselines across visually challenging Atari 100k tasks, memory-demanding benchmark, and 3D first-person ViZDoom environments.
  arXiv  Detail & Related papers  (2025-02-01T15:49:59Z)
• DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model [65.43473733967038]
  We introduce DrivingDojo, the first dataset tailor-made for training interactive world models with complex driving dynamics. Our dataset features video clips with a complete set of driving maneuvers, diverse multi-agent interplay, and rich open-world driving knowledge.
  arXiv  Detail & Related papers  (2024-10-14T17:19:23Z)
• The Dawn of Video Generation: Preliminary Explorations with SORA-like Models [14.528428430884015]
  High-quality video generation, encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation, holds considerable significance in content creation. Models like SORA have advanced generating videos with higher resolution, more natural motion, better vision-language alignment, and increased controllability.
  arXiv  Detail & Related papers  (2024-10-07T17:35:10Z)
• iVideoGPT: Interactive VideoGPTs are Scalable World Models [70.02290687442624]
  World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. This work introduces Interactive VideoGPT, a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations.
  arXiv  Detail & Related papers  (2024-05-24T05:29:12Z)

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.