VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs

• URL: http://arxiv.org/abs/2603.17652v1
• Date: Wed, 18 Mar 2026 12:13:30 GMT
• Title: VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
• Abstract summary: We propose VectorWorld, a streaming world model that incrementally generates ego-centric vectorgraph tiles during rollouts.<n>It aligns with history-conditioned policies by producing a policy-compatible interaction state via a motion-aware gated VAE.<n>It supports real-time outstep completion via solverfreegated Diconditioned trained MeanFlow JVP.
• Score: 10.040683730802266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due to (i) history-free initialization that mismatches policy inputs, (ii) multi-step sampling latency that violates real-time budgets, and (iii) compounding kinematic infeasibility over long horizons. We propose VectorWorld, a streaming world model that incrementally generates ego-centric $64 \mathrm{m}\times 64\mathrm{m}$ lane--agent vector-graph tiles during rollout. VectorWorld aligns initialization with history-conditioned policies by producing a policy-compatible interaction state via a motion-aware gated VAE. It enables real-time outpainting via solver-free one-step masked completion with an edge-gated relational DiT trained with interval-conditioned MeanFlow and JVP-based large-step supervision. To stabilize long-horizon rollouts, we introduce $Δ$Sim, a physics-aligned non-ego (NPC) policy with hybrid discrete--continuous actions and differentiable kinematic logit shaping. On Waymo open motion and nuPlan, VectorWorld improves map-structure fidelity and initialization validity, and supports stable, real-time $1\mathrm{km}+$ closed-loop rollouts (\href{https://github.com/jiangchaokang/VectorWorld}{code}).

Related papers

• FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation [18.092834753587454]
  FlowPilot is a compact world-action model for real-time onboard UAV navigation from depth.<n>A dual-stream mixture-of-transformers couples video and action experts through shared attention, allowing future-scene prediction and trajectory generation to inform each other.
  arXiv  Detail & Related papers  (2026-08-01T12:43:31Z)
• Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstration [0.01268579273097071]
  Generative models excel at capturing multimodal behaviors for robotic Learning from Demonstration (LfD), but often suffer from high inference cost.<n>This paper introduces Temporal Policy, a generative framework based on interpolants that formulates action generation as a temporally coupled transport problem.<n>We validate Temporal Policy across visuomotor simulation benchmarks and on a physical Barrett WAM 2x 7DoF platform.
  arXiv  Detail & Related papers  (2026-07-31T14:47:02Z)
• PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation [10.164953732323463]
  PIER-Flow is a lightweight navigation policy for mobile robots.<n>It achieves a 98.85% success rate and zero collisions, with an average inference of $sim$1.29 ms.
  arXiv  Detail & Related papers  (2026-07-11T12:34:28Z)
• Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation [58.86413499077093]
  We present textbfemphPoint as Skeleton, a generative sensor simulation framework for state-updated autoregressive driving video generation.<n>To support closed-loop rollout, we introduce Reset-and-Roll, which adapts rolling diffusion inference to simulation.<n>Experiments on nuScenes and nuPlan show that textitPoint as Skeleton improves autoregressive generation quality during closed-loop rollout.
  arXiv  Detail & Related papers  (2026-07-07T17:20:51Z)
• CausalDrive: Real-time Causal World Models for Autonomous Driving [60.66609721457312]
  We present CausalDrive, a controllable, real-time foundation driving world.<n>CaulDrive operates solely on the initial front-view frame, the ego-vehicle's trajectory, and a macroscopic text prompt.<n>We demonstrate its versatility across three downstream applications: (1) generative closed-loop evaluation with significantly mitigated collision artifacts, (2) large-scale Reinforcement Learning (RL) post-training driven by a Video2Reward module, and (3) real-time human-in-the-loop simulation.
  arXiv  Detail & Related papers  (2026-06-13T15:04:44Z)
• Composable Model-Free RL for Navigation with Input-Affine Systems [3.2917282915992883]
  As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time.<n>We propose a composable, model-free reinforcement learning method that learns a value function and an optimal policy for each individual environment element.
  arXiv  Detail & Related papers  (2026-02-13T00:19:35Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Pseudo-Simulation for Autonomous Driving [66.1981253104508]
  Existing evaluation paradigms for Autonomous Vehicles (AVs) face critical limitations.<n>Real-world evaluation is often challenging due to safety concerns and a lack of realism.<n>Open-loop evaluation relies on metrics that generally overlook compounding errors.
  arXiv  Detail & Related papers  (2025-06-04T17:57:53Z)
• FLARE: Robot Learning with Implicit World Modeling [87.81846091038676]
  $textbfFLARE$ integrates predictive latent world modeling into robot policy learning.<n>$textbfFLARE$ achieves state-of-the-art performance, outperforming prior policy learning baselines by up to 26%.<n>Our results establish $textbfFLARE$ as a general and scalable approach for combining implicit world modeling with high-frequency robotic control.
  arXiv  Detail & Related papers  (2025-05-21T15:33:27Z)
• Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model [63.336123527432136]
  We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation.<n>Unlike existing video generative models for autonomous driving, the proposed designs are tailored for interactive simulation.<n>We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-11T06:35:18Z)

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.