# LongVie 2: Multimodal Controllable Ultra-Long Video World Model arXiv: https://arxiv.org/abs/2512.13604 ยท HTML: https://mlsanity.com/paper/2512.13604/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Video-generation world models and simulators, one of 11 directions in World models. - Builds on 41 of its 51 references that are in the map. - First posted on arXiv 15 Dec 2025. ## Placed in - World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/) ## Builds on (most cited first, 30 of 41) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024) - [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024) - [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024) - [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024) - [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025) - [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024) - [Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image](https://mlsanity.com/paper/2012.09855/) (2020) - [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025) - [Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://mlsanity.com/paper/2401.15977/) (2024) - [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025) - [MovieNet: A Holistic Dataset for Movie Understanding](https://mlsanity.com/paper/2007.10937/) (2020) - [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025) - [Matrix-game 2.0: An open-source real-time and streaming interactive world model](https://mlsanity.com/paper/2508.13009/) (2025) - [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025) - [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024) - [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://mlsanity.com/paper/2311.16933/) (2023) - [GameFactory: Creating New Games with Generative Interactive Videos](https://mlsanity.com/paper/2501.08325/) (2025) - [Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise](https://mlsanity.com/paper/2501.08331/) (2025) - [Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control](https://mlsanity.com/paper/2503.14492/) (2025) - [Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition](https://mlsanity.com/paper/2506.17201/) (2025) - [RELIC: Interactive Video World Model with Long-Horizon Memory](https://mlsanity.com/paper/2512.04040/) (2025) - [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025) - [Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout](https://mlsanity.com/paper/2511.20649/) (2025) ## Built on by (most cited first, 9 of 9) - [WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG](https://mlsanity.com/paper/2603.23497/) (2026) - [ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling](https://mlsanity.com/paper/2603.02697/) (2026) - [SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing](https://mlsanity.com/paper/2603.08982/) (2026) - [MemCam: Memory-Augmented Camera Control for Consistent Video Generation](https://mlsanity.com/paper/2603.26193/) (2026) - [OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation](https://mlsanity.com/paper/2605.13815/) (2026) - [DisCo: World Models with Discrete Camera Motion Control](https://mlsanity.com/paper/2606.07967/) (2026) - [HelloWorld: Enabling Socially Interactive Characters in Video World Models](https://mlsanity.com/paper/2608.05070/) (2026) - [LongLive-Plug: Once-for-All Distillation for Video Generation](https://mlsanity.com/paper/2609.38154/) (2026) - [Connected Self Forcing: Beyond Local Learning in Video Autoregression](https://mlsanity.com/paper/2610.12156/) (2026) ## Abstract (arXiv) Building video world models upon pretrained video generation systems represents an important yet challenging step toward general spatiotemporal intelligence. A world model should possess three essential properties: controllability, long-term visual quality, and temporal consistency. To this end, we take a progressive approach-first enhancing controllability and then extending toward long-term, high-quality generation. We present LongVie 2, an end-to-end autoregressive framework trained in three stages: (1) Multi-modal guidance, which integrates dense and sparse control signals to provide implicit world-level supervision and improve controllability; (2) Degradation-aware training on the input frame, bridging the gap between training and long-term inference to maintain high visual quality; and (3) History-context guidance, which aligns contextual information across adjacent clips to ensure temporal consistency. We further introduce LongVGenBench, a comprehensive benchmark comprising 100 high-resolution one-minute videos covering diverse real-world and synthetic environments. Extensive experiments demonstrate that LongVie 2 achieves state-of-the-art performance in long-range controllability, temporal coherence, and visual fidelity, and supports continuous video generation lasting up to five minutes, marking a significant step toward unified video world modeling.