Open Source
What Should World Models Forget? Stratified Retention for Continual Adaptation
arXiv eess.SP0 views
arXiv:2610.03713v2 Announce Type: replace-cross Abstract: Continual learning treats any drop in performance on previously seen data as forgetting, a convention inherited from settings where the prediction target is stationary. World models violate this assumption: their target is the environment, which changes, so knowledge that was accurate when learned can later become false, and revising it is correct behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but it has not been formulated for world models, which are distinctive in that they also encode structural knowledge, such as physical laws and object permanence, that must never be degraded. We argue that continual world models need retention stratified by invariance timescale, the time over which knowledge stays true: invariants should be refined but never degraded, while instance-level facts should be revised once the environment changes. We show that standard forgetting metrics, used alone, count correct revision as forgetting and so rank a frozen model highest. We propose differential retention, which reports two quantities separately: invariant retention, checked after every adaptation round, and revision latency, the number of observations a model needs to pick up a change.
Source:https://arxiv.org/abs/2610.03713PreviousSensing-Aided Beam Selection for UAV NetworksNextLightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer
Related posts
Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift
0arXiv eess.IV
X-Strata: Separating Aneurysms and Overlapping Vessels into Layers from 2D X-ray Angiography
0arXiv eess.IV
uhd-rfsoc: Bringing Off-the-Shelf RFSoC Boards to Unmodified UHD Applications
0arXiv eess.SP
An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems
0arXiv cs.MA
From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
0arXiv cs.MA
A Taxonomy of Real Faults in Hybrid Quantum-Classical Architectures
0arXiv cs.SE