AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization

• URL: http://arxiv.org/abs/2606.07326v1
• Date: Fri, 05 Jun 2026 14:43:13 GMT
• Title: AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
• Abstract summary: AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
• Score: 79.26935895370191
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics.

Related papers

• DWMP: Leveraging Dual World Models for Humanoid Obstacle Traversal [6.144157194223047]
  We propose a framework that provides the actor with separate but complementary world-model representations for humanoid obstacle traversal.<n>A Koopman-based dynamics world model lifts proprioceptive observations into a latent space where their temporal evolution is approximately linear.<n>An RSSM-based visual world model compresses egocentric depth observations into compact states while preserving obstacle-related geometry.<n> Experiments in simulation and on a Unitree G1 humanoid robot show that DWMP improves obstacle performance over baselines and supports real-world deployment.
  arXiv  Detail & Related papers  (2026-09-11T02:13:19Z)
• Real-Time Human-Centric World Modeling for Upper-Body Human-Object Interaction [15.252158606421752]
  We present a real-time human-centric world model for upper-body interactive generation, aiming to synthesize coherent local world dynamics centered on a person.<n>We adopt a continuous-discrete joint control scheme with two complementary components: a continuous human state and a discrete interaction state.<n>Experiments demonstrate improved fine-grained motion fidelity, more hand-object coordination, and effective real-time interaction.
  arXiv  Detail & Related papers  (2026-07-26T07:34:14Z)
• 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)
• AtomicMotion: Learning Human Motion From Different Human Parts [9.72019653340761]
  We present AtomicMotion, a framework designed to decouple and re-integrate body dynamics through three core innovations.<n>First, we introduce a logical body partitioning scheme that decomposes the skeleton into five distinct clusters based on functional intent.<n>Second, to robustly map sparse inputs to high-dimensional poses, we employ a masked full-body pre-conditioning strategy.<n>Third, addressing the limitations of vanilla spatial attention, we propose Kinematic Attention.
  arXiv  Detail & Related papers  (2026-05-21T15:39:38Z)
• SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance [49.69016078147708]
  Accurately reconstructing human behavior in close-interaction scenarios is crucial for enabling realistic virtual interactions in augmented reality.<n>We propose SocialMirror, a diffusion-based framework that integrates semantic and geometric cues to effectively address these issues.<n>SocialMirror achieves state-of-the-art performance in reconstructing interactive human meshes, demonstrating strong generalization across unseen datasets and in-the-wild scenarios.
  arXiv  Detail & Related papers  (2026-04-15T07:41:52Z)
• Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation [57.28703268044067]
  We propose Cortical Policy, a novel dual-stream view transformer for robotic manipulation.<n>Our framework offers a fresh perspective for robotic manipulation and holds potential for broader application in vision-based robot control.
  arXiv  Detail & Related papers  (2026-03-22T04:18:54Z)
• EgoForge: Goal-Directed Egocentric World Simulator [26.712565464146937]
  EgoForge is a goal-directed world simulator that generates coherent, first-person video rollouts from minimal static inputs.<n>VideoDiffusionNFT is a trajectory-level reward-guided refinement that optimize goal completion, temporal causality, scene consistency, and perceptual fidelity during diffusion sampling.
  arXiv  Detail & Related papers  (2026-03-20T17:46:55Z)
• Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning [61.753025885751036]
  We introduce the Ego-to-World benchmark, which evaluates a vision-language model's ability to fuse heterogeneous viewpoints across three tasks.<n>We propose CoRL, a two-stage framework that combines Chain-of-Thought supervised fine-tuning with reinforcement learning.<n>We show that CoRL consistently surpasses strong proprietary and open-source baselines on both reasoning and perception-grounding metrics.
  arXiv  Detail & Related papers  (2026-03-16T04:27:53Z)
• Self-motion as a structural prior for coherent and robust formation of cognitive maps [31.112944521126135]
  We show that self-motion can act as a structural prior that actively organizes the geometry of learned cognitive maps.<n>We embed a path-integration-based motion prior in a predictive-coding framework, implemented using a capacity-efficient, brain-inspired recurrent mechanism.<n>Mechanistic analyses reveal that the motion prior itself encodes geometrically precise trajectories under tight constraints.
  arXiv  Detail & Related papers  (2025-12-23T04:28:52Z)
• ECHO: Ego-Centric modeling of Human-Object interactions [71.17118015822699]
  ECHO (Ego-Centric modeling of Human-Object interactions) is developed.<n>It recovers three modalities: human pose, object motion, and contact from such minimal observation.<n>It outperforms existing methods that do not offer the same flexibility.
  arXiv  Detail & Related papers  (2025-08-29T12:12:22Z)

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.