Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
- URL: http://arxiv.org/abs/2608.29910v1
- Date: Sun, 30 Aug 2026 17:11:00 GMT
- Title: Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
- Abstract summary: We present Matrix-Game 3.5, which advances real-time interactive world generation through three key improvements.<n>First, we propose a unified geometry-aware memory framework, whose patch-memory and tiled-PRoPE components introduce no additional learnable parameters.<n>Second, we introduce a static-dynamic disentangled world representation that separately models static scene geometry and dynamic subjects.<n>Third, we develop a two-stage progressive real-time distillation framework that converts a bidirectional diffusion model into a few-step causal generator.
- Score: 28.887112448832525
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics, embodied agents, and XR. Achieving stable long-horizon interactive generation, however, remains challenging, as the model must simultaneously preserve scene geometry, dynamic consistency, and camera control while supporting real-time autoregressive generation. Building upon Matrix-Game 3.0, we present Matrix-Game 3.5, as shown in Figure 1, which advances real-time interactive world generation toward geometry-aware and long-horizon consistent simulation through three key improvements. First, we propose a unified geometry-aware memory framework, whose patch-memory and tiled-PRoPE components introduce no additional learnable parameters, combining explicit 3D patch retrieval with projective camera conditioning to enable geometry-consistent camera control and faithful long-horizon scene recall. Second, we introduce a static-dynamic disentangled world representation that separately models static scene geometry and dynamic subjects, preserving both geometric consistency and subject identity throughout long-horizon generation. Third, we develop a two-stage progressive real-time distillation framework that converts a bidirectional diffusion model into a few-step causal generator through Perceptual Flow Matching and curriculum based Self-Rollout DMD, enabling minute-long real-time interactive generation. Extensive experiments demonstrate that, with a unified training corpus spanning Unreal simulation environments, open-world games, and internet videos, MatrixGame 3.5 achieves strong performance in long-horizon scene recall, precise camera control, subject consistency, prompt-driven world generation, and stable real-time open-world interaction.
Related papers
- MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data [125.43597497646444]
MetaWorld is a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos.<n>It achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.
arXiv Detail & Related papers (2026-06-01T18:20:20Z) - Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory [53.39687409541093]
Matrix-Game 3.0 is a memory-augmented interactive world model designed for 720p real-time longform video generation.<n>We introduce systematic improvements across data, model, and inference.<n> Experimental results show that Matrix-Game 3.0 achieves up to 40 FPS real-time generation at 720p resolution with a 5B model.
arXiv Detail & Related papers (2026-04-10T06:00:09Z) - WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation [47.97929550105451]
We establish camera pose as a unifying geometric representation to ground immediate action control and long-term 3D consistency.<n>Our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.
arXiv Detail & Related papers (2026-03-17T17:59:56Z) - Beyond Pixel Histories: World Models with Persistent 3D State [50.4601060508243]
PERSIST is a new paradigm of world model which simulates the evolution of a latent 3D scene.<n>We show substantial improvements in spatial memory, 3D consistency, and long-horizon stability over existing methods.
arXiv Detail & Related papers (2026-03-03T19:58:31Z) - RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
arXiv Detail & Related papers (2026-02-24T08:41:40Z) - TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model [53.555353366322464]
We present TeleWorld, a real-time multimodal 4D world modeling framework that unifies video generation, dynamic scene reconstruction, and long-term world memory within a closed-loop system.<n>Our approach achieves seamless integration of dynamic object modeling and static scene representation within a unified 4D framework, advancing world models toward practical, interactive, and computationally accessible synthesis systems.
arXiv Detail & Related papers (2025-12-31T18:31:46Z) - RELIC: Interactive Video World Model with Long-Horizon Memory [74.81433479334821]
A truly interactive world model requires real-time long-horizon streaming, consistent spatial memory, and precise user control.<n>We present RELIC, a unified framework that tackles these three challenges altogether.<n>Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time.
arXiv Detail & Related papers (2025-12-03T18:29:20Z) - Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model [15.16063778402193]
Matrix-Game 2.0 is an interactive world model generates long videos on-the-fly via few-step auto-regressive diffusion.<n>It can generate high-quality minute-level videos across diverse scenes at an ultra-fast speed of 25 FPS.
arXiv Detail & Related papers (2025-08-18T15:28:53Z)
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.