World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks

• URL: http://arxiv.org/abs/2605.19957v1
• Date: Tue, 19 May 2026 15:10:27 GMT
• Title: World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
• Abstract summary: We introduce emphWorld-Ego Modeling, a new conceptual paradigm that decomposes future evolution into world and ego components.<n>We instantiate this paradigm as the World-Ego Model (WEM), a unified embodied world model that couples an implicit separate world-ego planner with a cascade-parallel mixture-of-experts (CP-MoE) diffusion generator.
• Score: 62.389116510844445
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: World models are widely explored in embodied intelligence, yet they typically predict distinct evolutions of the world and the ego within a single stream, where the world captures persistent instruction-agnostic scene regularities and the ego captures robot-centric instruction-conditioned dynamics. This world-ego entanglement leads to a degradation in long-horizon embodied scenarios, particularly in hybrid tasks with interleaved navigation and manipulation behaviors. In this paper, we introduce \emph{World-Ego Modeling}, a new conceptual paradigm that decomposes future evolution into world and ego components. We define the world-ego boundary from three perspectives, i.e., motion-, semantic-, and intention-based views, and analyze three disentanglement strategies with post-, pre-, and full disentanglement. Further, we instantiate this paradigm as the World-Ego Model (WEM), a unified embodied world model that couples an implicit separate world-ego planner with a cascade-parallel mixture-of-experts (CP-MoE) diffusion generator. To enable rigorous evaluation, we further construct HTEWorld, the first benchmark for long-horizon world modeling with hybrid navigation-manipulation tasks, providing 125K video clips (over 4.5M frames) with fine-grained action annotations and 300 multi-turn evaluation trajectories (over 2K instructions). Extensive experiments show that WEM achieves state-of-the-art performance on HTEWorld while remaining competitive on existing manipulation-only benchmarks.

Related papers

• NavWM: A Unified Navigation World Model for Foresight-Driven Planning [15.801647085785826]
  NavWM is a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation.<n>To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework.<n>Experiments across diverse datasets demonstrate that NavWM significantly advances the state-the-art.
  arXiv  Detail & Related papers  (2026-06-23T03:30:20Z)
• GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving [56.50032398571235]
  GraphWorld is an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling.<n>We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents.<n>This latent world state captures key interaction dynamics and safety-relevant semantics, and serves as a conditioning signal to guide long-horizon, safety-aware trajectory planning.
  arXiv  Detail & Related papers  (2026-06-15T06:26:46Z)
• 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)
• Xiaomi EV World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving [51.90209659403234]
  This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving.<n>For world representation, we propose WorldRec, a feed-forward reconstruction architecture driven by sparse scene queries.<n>For world generation, we propose WorldGen, a two-stage training framework of bidirectional pretraining followed by causal fine-tuning.
  arXiv  Detail & Related papers  (2026-05-18T09:46:16Z)
• WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform [130.8118909583659]
  We introduce WorldArena 2.0, an expanded benchmark for embodied world model evaluation.<n>WorldArena 2.0 systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform.<n>Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance.
  arXiv  Detail & Related papers  (2026-05-18T06:18:21Z)
• The DAWN of World-Action Interactive Models [30.798493550954703]
  World prediction and action generation is treated as either isolated parallel branches or rigid predict-then-plan pipelines.<n>We instantiate this perspective with textbfDAWN (textbfDenoising textbfActions and textbfWorld itextbfNteractive model), a simple yet strong latent generative baseline.<n>DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks.
  arXiv  Detail & Related papers  (2026-05-12T05:30:00Z)
• Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models [39.648000265543445]
  Video-based world models have emerged along two dominant paradigms: video generation and 3D reconstruction.<n>We argue that the future of world modeling lies in 4D generation, which jointly models spatial structure and temporal evolution.<n>We propose Omni--WorldBench, a benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings.
  arXiv  Detail & Related papers  (2026-03-23T17:10:29Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning [52.36434784963598]
  We introduce WorldPrediction, a video-based benchmark for evaluating world modeling and procedural planning capabilities of different AI models.<n>We show that current frontier models barely achieve 57% accuracy on WorldPrediction-WM and 38% on WorldPrediction-PP whereas humans are able to solve both tasks perfectly.
  arXiv  Detail & Related papers  (2025-06-04T18:22:40Z)

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.