Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Shukrullo Nazirjonov, Sai Prasanna, Anna Manasyan, Georg Martius
• Venue: arXiv: cs.CV
• Published: 2026-08-12
• Collected: 2026-08-13
• URL: http://arxiv.org/abs/2608.12078v1
• PDF: https://arxiv.org/pdf/2608.12078v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The research focuses on object-centric world models (OCWMs) for artificial intelligence agents. The study compares OCWMs with traditional scene-centric models in terms of representation quality, planning success, and robustness under distribution shifts. The findings suggest that OCWMs with high-quality object-centric representations outperform scene-centric models in planning tasks, and they are more robust to unseen distribution shifts when using well-bound slots.

What the Document Says

• The study investigates the performance of object-centric world models (OCWMs) for visual model-predictive control compared to scene-centric models. The research finds a positive correlation between planning success and unsupervised slot-quality metrics, with well-bound slots making auxiliary proprioception inputs unnecessary.
• The OCWM with well-bound slots is more robust overall than the end-to-end trained scene-centric LeWM, while DINO-WM remains competitive under unseen distribution shifts.

Key Concepts Mentioned

• object-centric world models (OCWMs)
• visual model-predictive control
• scene-centric models
• slot quality
• planning success
• distribution shift

Claims Made by the Document

• The object-centric bias in OCWMs leads to better performance for planning tasks.
• Well-bound slots in OCWMs make auxiliary proprioception inputs unnecessary.
• OCWMs with well-bound slots are more robust than scene-centric LeWM under unseen distribution shifts.

Evidence Used

• Correlation between planning success and unsupervised slot-quality metrics
• Performance comparison of OCWMs and scene-centric models under distribution shifts

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a set of slots that bind to its objects, have been proposed as an inductive bias for world models that are more sample-efficient and generalize better. Yet prior object-centric world models (OCWMs) take the slot encoder as given and evaluate only in-distribution, leaving open whether the object-centric bias actually delivers for planning and what within the OCWM drives it. We conduct a controlled study of OCWMs for visual model-predictive control along two axes: object-centric representation quality and generalization under distribution shift relative to scene-centric models. We find that (i) planning success correlates positively with unsupervised slot-quality metrics (FG-ARI, mBO), though the gains saturate at high slot quality; (ii) with well-bound slots, the auxiliary proprioception inputs and masking inductive bias that prior methods relied on become unnecessary; and (iii) under unseen distribution shifts, the OCWM with well-bound slots is more robust overall than the end-to-end trained scene-centric LeWM, while DINO-WM, built on similar frozen pretrained features, remains competitive -- pointing to pretrained features as a key contributor to robustness.