Attenuated in-context identification in time-series foundation models: diagnosis under counterfactual inputs and repair by synthetic forced-system fine-tuning
cs.LG, cs.SY, eess.SY
Submitted: 2026-10-06
Updated: 2026-10-06
Comments: 12 pages, 4 figures, 5 tables
Code: https://github.com/forgi86/sysid-transformers
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Chronos-2: From Univariate to Universal Forecasting
- A decoder-only foundation model for time-series forecasting
- From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
- Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
- Causal Analysis for Time Series Foundation Models
- Zero-shot forecasting of chaotic systems
- Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
- ThermoForce: A Physics-Structured Interventional World Model for Building HVAC Control
- From system models to class models: An in-context learning paradigm
- Enhanced Transformer architecture for in-context learning of dynamical systems
- On the adaptation of in-context learners for system identification
- On Foundation Models for Dynamical Systems from Purely Synthetic Data
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks