LyTimeT: Towards Robust and Interpretable State-Variable Discovery

• URL: http://arxiv.org/abs/2510.19716v1
• Date: Wed, 22 Oct 2025 16:03:10 GMT
• Title: LyTimeT: Towards Robust and Interpretable State-Variable Discovery
• Authors: Kuai Yu, Crystal Su, Xiang Liu, Judah Goldfeder, Mingyuan Shao, Hod Lipson,
• Abstract summary: LyTimeT is a framework for interpretable variable extraction.<n>It learns robust and stable latent representations of dynamical video systems.<n>Our results demonstrate that combiningtemporal attention with stability constraints yields predictive models.
• Score: 7.505092370141079
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Extracting the true dynamical variables of a system from high-dimensional video is challenging due to distracting visual factors such as background motion, occlusions, and texture changes. We propose LyTimeT, a two-phase framework for interpretable variable extraction that learns robust and stable latent representations of dynamical systems. In Phase 1, LyTimeT employs a spatio-temporal TimeSformer-based autoencoder that uses global attention to focus on dynamically relevant regions while suppressing nuisance variation, enabling distraction-robust latent state learning and accurate long-horizon video prediction. In Phase 2, we probe the learned latent space, select the most physically meaningful dimensions using linear correlation analysis, and refine the transition dynamics with a Lyapunov-based stability regularizer to enforce contraction and reduce error accumulation during roll-outs. Experiments on five synthetic benchmarks and four real-world dynamical systems, including chaotic phenomena, show that LyTimeT achieves mutual information and intrinsic dimension estimates closest to ground truth, remains invariant under background perturbations, and delivers the lowest analytical mean squared error among CNN-based (TIDE) and transformer-only baselines. Our results demonstrate that combining spatio-temporal attention with stability constraints yields predictive models that are not only accurate but also physically interpretable.

Related papers

• LEVDA: Latent Ensemble Variational Data Assimilation via Differentiable Dynamics [6.953554594702111]
  We propose Latent Ensemble Data Assimilation (LEVDA), an ensemble-space variational smoother.<n>It assimilates states and unknown parameters without the need for adjoint code or auxiliary observation-to-latent encoders.<n>It substantially improved assimilation accuracy and computational efficiency compared to full-state 4DEnVar.
  arXiv  Detail & Related papers  (2026-02-23T00:54:59Z)
• Flexible Gravitational-Wave Parameter Estimation with Transformers [73.44614054040267]
  We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time.<n>We demonstrate that a single flexible model -- called Dingo-T1 -- can analyze 48 gravitational-wave events from the third LIGO-Virgo-KAGRA Observing Run.
  arXiv  Detail & Related papers  (2025-12-02T17:49:08Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Randomized Space-Time Sampling for Affine Graph Dynamical Systems [3.8379346559198235]
  We consider signals evolving over time according to a linear dynamical system on a graph, where both the initial state and the source term are bandlimited.<n>We introduce two random space-time sampling regimes and analyze the conditions under which stable recovery is achievable.
  arXiv  Detail & Related papers  (2025-09-20T21:43:05Z)
• Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations [51.510040541600176]
  This work proposes modeling continuous-time rotational object dynamics on $SO(3)$.<n>Unlike existing methods that rely on simplified motion assumptions, our method learns a general latent dynamical system of the underlying object trajectory.<n> Experimental results on real-world data demonstrate compelling forecasting capabilities compared to existing approaches.
  arXiv  Detail & Related papers  (2025-06-07T12:41:50Z)
• Beyond Fixed Variables: Expanding-variate Time Series Forecasting via Flat Scheme and Spatio-temporal Focal Learning [9.205228068704141]
  In real-world applications, Cyber-Physical Systems often expand as new sensors are, increasing variables in MTSF.<n>This task presents unique challenges, specifically (1) handling inconsistent data caused by adding new variables, and (2) addressing imbalanced-temporal learning.<n>To address these challenges, we propose STEV, a flexible-temporal forecasting framework.
  arXiv  Detail & Related papers  (2025-02-21T08:43:26Z)
• Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks [3.1484174280822845]
  We present a method to jointly solve the sensing and model identification problems with simple implementation, efficient, and robust performance.<n>SINDy-SHRED uses Gated Recurrent Units to model sparse sensor measurements along with a shallow network decoder to reconstruct the full-temporal field from the latent state space.<n>We conduct systematic experimental studies on PDE data such as turbulent flows, real-world sensor measurements for sea surface temperature, and direct video data.
  arXiv  Detail & Related papers  (2025-01-23T02:18:13Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis [3.686808512438363]
  We introduce 'DualDynamics', a novel framework that combines NDE-based method and Neural Flow-based method.<n>This approach enhances expressive power while balancing computational demands, addressing critical limitations of existing techniques.<n>Our results show consistent out-performance over state-of-the-art methods, indicating DualDynamics' potential to advance irregular time series analysis significantly.
  arXiv  Detail & Related papers  (2024-01-10T07:51:02Z)
• EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision [85.17951804790515]
  EmerNeRF is a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. It simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. Our method achieves state-of-the-art performance in sensor simulation.
  arXiv  Detail & Related papers  (2023-11-03T17:59:55Z)
• Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignments [110.79706180350507]
  We show that our proposed loss can be used to define temporal-temporal baryechecenters as Fr'teche means duality. Experiments on handwritten letters and brain imaging data confirm our theoretical findings.
  arXiv  Detail & Related papers  (2022-03-11T09:46:22Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.