paper-with-me

Papers

Latent State Design for World Models under Sufficiency Constraints

2026-05-03 · Keon Woo Kim arxiv

A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and support some future function: prediction, control, planning, memory, grounding, or counterfactual reasoning. This paper treats world-model research as latent state design under sufficiency constraints. We propose a functional taxonomy that groups methods by what their latent state is for, rather than by architecture or application domain: predictive embedding, recurrent belief state, object/causal structure, latent action interface, grounded planning interface, and memory substrate. These roles expose distinctions that architecture-based groupings hide, including the gap between predictive sufficiency and control sufficiency, and the gap between passive video prediction and counterfactual action modeling. The taxonomy supports an evaluation framework that judges a model by the sufficiency constraint its latent state was built to satisfy. We compare methods along seven axes: representation, prediction, planning, controllability, causal/counterfactual support, memory, and uncertainty. We use the resulting matrix as a diagnostic for what a latent state preserves, discards, and enables. The conclusion that follows is that an actionable world model is the one whose state construction matches the task, not the one that preserves the most information.

📄 PDF Abstract BibTeX arXiv:2605.01694

Code (0)

등록된 구현이 없습니다.

Tasks

Video Prediction

Similar Papers 제목 키워드 기반

InvarGC: Invariant Granger Causality for Heterogeneous Interventional Time Series under Latent Confounding

2025-10-22 · Ziyi Zhang, Shaogang Ren, Xiaoning Qian, Nick Duffield arxiv

Granger causality is widely used for causal structure discovery in complex systems from multivariate time series data. Traditional Granger causality tests based on linear models often fail to detect even mild non-linear …

Unifying Invariant and Variant Features for Graph Out-of-Distribution via Probability of Necessity and Sufficiency

2024-07-21 · Xuexin Chen, Ruichu Cai, Kaitao Zheng, Zhifan Jiang 외

Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has considerable real-world applications. One of the most mainstream methods is to extract the invariant s…

Graph Learning

Relational Causal Discovery with Latent Confounders

2025-07-02 · Matteo Negro, Andrea Piras, Ragib Ahsan, David Arbour 외 arxiv

Estimating causal effects from real-world relational data can be challenging when the underlying causal model and potential confounders are unknown. While several causal discovery algorithms exist for learning causal mod…

Causal Inference

MDL Meets Latent Confounders: LNML-based Causal Discovery

2026-07-05 · Zhongyi Que, Shin Matsushima, Kenji Yamanishi arxiv

Causal discovery with nonlinear mechanisms and latent confounders remains challenging. Existing methods often rely on either linear assumptions or causal sufficiency, limiting their applicability. We propose an MDL-based…

From Local to Cluster: A Unified Framework for Causal Discovery with Latent Variables

2026-04-24 · Zongyu Li arxiv

Latent variables pose a fundamental challenge to causal discovery and inference. Conventional local methods focus on direct neighbors but fail to provide macro level insights. Cluster level methods enable macro causal re…

Computational EfficiencyCausal Inference