SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2608.22750 · 2026

MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models

Miao Liu, Haoxiang Huang, Shiji Zhou, Xiang Liu, Sen Cui, Yueqing Sun, Qi Gu, Zhekai Wang, Zhikang Chen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Object-centric world models forecast future videos by evolving a set of entity slots, but the variables receiving dynamics supervision are often unconstrained visual features. We introduce MOSH-WM, a mask-grounded soft-Hamiltonian world model that makes its position-like state explicitly depend on slot-owned image support. A frozen video-slot encoder produces slots and masks; spatial moments of mask-owned support form a canonical state Q, temporal differences form P , and a learned energy supplies a soft directional bias to a bounded learned increment. Decoder-relevant appearance and identity are stored separately in a causal visual context. A gated composer and bounded residual then combine this context with the propagated phase state to reconstruct decoder-compatible slots. On OBJ3D, given six observed frames and evaluated over the following 30 frames, MOSH-WM reduces LPIPS by 25.0% and spatial MSE by 33.7% relative to the strongest object-centric baseline. On CLEVRER, given six observed frames and evaluated over the following ten frames, the corresponding reductions are 14.5% and 18.7%. Horizon-resolved visual and object-state measurements show that the complete model accumulates error more slowly throughout the 30-frame closed-loop rollout. Project page: https://github.com/moshwm-anon/-moshwm-anon.github.io.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2608.22750")
get_code_for_paper("2608.22750")
have("2608.22750")

Connect an agent — have() is free.