Cover Image

The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Internò, Christian, Yamaguchi, Jumpei, Amdahl-Culleton, Loren, Olhofer, Markus, Klindt, David, Hammer, Barbara
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AI-Generated Video Detection via Perceptual Straightening
by: Internò, Christian, et al.
Published: (2025)

Federated Loss Exploration for Improved Convergence on Non-IID Data
by: Internò, Christian, et al.
Published: (2025)

FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios
by: Moleri, Andrea, et al.
Published: (2026)

Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring
by: Internò, Christian, et al.
Published: (2024)

Industrial Energy Disaggregation with Digital Twin-generated Dataset and Efficient Data Augmentation
by: Internò, Christian, et al.
Published: (2025)

Data Whitening Improves Sparse Autoencoder Learning
by: Saraswatula, Ashwin, et al.
Published: (2025)

The Narcissus Hypothesis: Descending to the Rung of Illusion
by: Cadei, Riccardo, et al.
Published: (2025)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
by: Ibrahim, Mark, et al.
Published: (2024)

No learning rates needed: Introducing SALSA -- Stable Armijo Line Search Adaptation
by: Kenneweg, Philip, et al.
Published: (2024)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Towards Understanding the Influence of Training Samples on Explanations
by: Artelt, André, et al.
Published: (2024)

Fairness-Enhancing Ensemble Classification in Water Distribution Networks
by: Strotherm, Janine, et al.
Published: (2024)

The Effect of Data Poisoning on Counterfactual Explanations
by: Artelt, André, et al.
Published: (2024)

Physics-Informed Graph Neural Networks for Water Distribution Systems
by: Ashraf, Inaam, et al.
Published: (2024)

Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
by: Zhang, Yufei, et al.
Published: (2024)

LLM as a code generator in Agile Model Driven Development
by: Sadik, Ahmed R., et al.
Published: (2024)

Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
by: Störck, Felix, et al.
Published: (2025)

Continuous Fair SMOTE -- Fairness-Aware Stream Learning from Imbalanced Data
by: Lammers, Kathrin, et al.
Published: (2025)

Improving Line Search Methods for Large Scale Neural Network Training
by: Kenneweg, Philip, et al.
Published: (2024)

One-Class Intrusion Detection with Dynamic Graphs
by: Liuliakov, Aleksei, et al.
Published: (2025)

Faster Convergence for Transformer Fine-tuning with Line Search Methods
by: Kenneweg, Philip, et al.
Published: (2024)

Learning Latent Dynamic Robust Representations for World Models
by: Sun, Ruixiang, et al.
Published: (2024)

Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
by: Levy, Jacob, et al.
Published: (2026)

Test-time Adaptation for Regression by Subspace Alignment
by: Adachi, Kazuki, et al.
Published: (2024)

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
by: Kunin, Daniel, et al.
Published: (2024)

Cross-Entropy Is All You Need To Invert the Data Generating Process
by: Reizinger, Patrik, et al.
Published: (2024)

Adapting World Models with Latent-State Dynamics Residuals
by: Lanier, JB, et al.
Published: (2025)

DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation
by: Liuliakov, Aleksei, et al.
Published: (2026)

Self-Improving World Modelling with Latent Actions
by: Qiu, Yifu, et al.
Published: (2026)

Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty
by: Roberts, Isaac, et al.
Published: (2025)

KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions
by: Fumagalli, Fabian, et al.
Published: (2024)

naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement
by: Kim, Hankyeol, et al.
Published: (2026)

Combinatorial Optimization with Policy Adaptation using Latent Space Search
by: Chalumeau, Felix, et al.
Published: (2023)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
by: Wang, Yiqi, et al.
Published: (2025)

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
by: Gospodinov, Emiliyan, et al.
Published: (2024)

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization
by: Röder, Frank, et al.
Published: (2025)

Asymmetrical Latent Representation for Individual Treatment Effect Modeling
by: Lacombe, Armand, et al.
Published: (2025)

Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
by: Chen, Jiayu, et al.
Published: (2025)

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
by: Wynn, Andrea, et al.
Published: (2025)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
by: Xu, Jiawei, et al.
Published: (2024)