Paper page - PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation

Source: https://huggingface.co/papers/2606.18375 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

PAIWorld enhances diffusion-transformer world models with geometric awareness and cross-view attention to improve multi-view 3D consistency for robotic manipulation tasks.

World foundation models(WFMs) are powerful simulators, yet they predominantly operate in a single-view setting and lack the multi-view3D consistencyrequired forrobotic manipulation. While robotic systems rely on multiple cameras (egocentric, eye-to-hand, and wrist-mounted) for policy learning, current multi-view world models simply concatenate view tokens without explicit geometric reasoning. This causes cross-view object drift, depth inconsistency, and texture misalignment. We trace these failures to two deficiencies: the absence of an explicit inter-view communication mechanism and the lack of a 3D geometric prior. We argue that resolving both simultaneously is necessary and sufficient. To address this, we present PAIWorld, a framework that augmentsdiffusion-transformerworld models via three core components: (1) Geometry-AwareCross-View Attentionblocks that establish an explicit pathway across views, (2)Geometric Rotary Position Embeddingthat encodes camera ray directions and extrinsic poses into the attention mechanism, and (3)Latent 3D-REPA, which distills 3D-aware features from frozen 3D foundation models to ensure3D consistency. Built upon a DiT-based world foundation model, PAIWorld achieves state-of-the-art multi-view3D consistencyonrobotic manipulationbenchmarks, ranking 1st on theWorldArenaleaderboard and 2nd on theAgiBot-Challenge2026leaderboard, while enabling downstream applications such as model-based planning, world action models, and multi-view policy post-training.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.18375

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.18375 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.18375 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.18375 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.