Skip to content
Preprint

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

Nov 2026 · 0 citations · 73 references
Computer Science

TL;DR

This work introduces a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator that mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation.

Abstract

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.

View source

Similar papers

Preprint Oct 2026

RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions

Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native control labels. We present RynnWorld-Latent, a cross-embodiment video world model that uses the 3D-grounded latent actions introduced by Rynn...

Hao-Yu Zhao, Yin-Zhou Tang, Zi-Xuan Wang et al. · 1 citation
Preprint Oct 2026

PRIME W0: Physical Priors from World Models for Embodied Manipulation

Vision-Language-Action (VLA) models excel at instruction following, yet most remain feed-forward: they condition actions only on the current observation and discard both long-horizon temporal context and the hierarchical structure of VLM representations. We present PRIME W0, a hierarchical conditional flow-matching fra...

Hua-Bin Peng, Fa-Gang Jin, Yang Wei et al. · 0 citations
Preprint Oct 2026

OpenWAM: An Open Framework for Composable World-Action Models

World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built ar...

Heng Yu, David Yuan, Ju-Ze Zhang et al. · 5 citations · ⚡1
Preprint Oct 2026

DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias pred...

Jun-Yan Li, Rui-Zhi Li, Yu Liu et al. · 2 citations
Preprint Nov 2026

Tiresias: Towards Language-Conditioned World Models

World models enable planning through internal simulation, while natural language provides intuitive task specification. Yet, language-conditioned world modeling remains fragmented across domains with disparate action spaces, datasets, and evaluation protocols. We introduce LCWM, a shared task that maps an initial agent...

Feng-Yi Wu, Yifei Dong, Ye-Tong Sha et al. · 0 citations
Sep 2026

WorldLine: Action-Driven Visual Simulation for Robotic Manipulation

WorldLine is introduced, an action-driven visual simulator that decouples transferable dynamics learning from heterogeneous action grounding and makes WorldLine a scalable and efficient visual simulator for policy evaluation and embodied planning.

Shenghe Zheng, Wen-Bo Li, Ji-Yao Zhang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.