FlowTSFM: Turning Encoder Depth into Quantile Transport

• URL: http://arxiv.org/abs/2609.13640v1
• Date: Sat, 12 Sep 2026 01:29:17 GMT
• Title: FlowTSFM: Turning Encoder Depth into Quantile Transport
• Abstract summary: We introduce FlowTSFM, an encoder architecture that interprets depth as a recurrent transport process.<n>With only 38.8M parameters, FlowTSFM achieves competitive performance on GIFT-Eval and TIME.<n>We also introduce CosMean, a scale-free diagnostic measuring whether recurrent updates consistently align toward the final prediction.
• Score: 29.781238027602466
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Encoder-based time series foundation models (TSFMs) typically rely on deep stacks of independently parameterized Transformer layers, where only the final forecast is supervised and intermediate representations have no explicit predictive role. We introduce FlowTSFM, an encoder architecture that interprets depth as a recurrent transport process: a single Transformer block is iteratively applied with shared parameters, while a quantile-flow objective supervises intermediate states along a prescribed trajectory from a prior distribution toward the final forecast. The objective combines pinball forecasting loss with path-level position matching. With only 38.8M parameters, FlowTSFM achieves competitive performance on GIFT-Eval and TIME, remaining within 1.8-4.6% MASE of stronger baselines while using approximately $3\times$ fewer parameters than a 12-layer Chronos-2 model (119.5M). Beyond accuracy, we introduce CosMean, a scale-free diagnostic measuring whether recurrent updates consistently align toward the final prediction. Under a matched intermediate-state probing protocol, FlowTSFM achieves a CosMean score of 0.919 compared with 0.350 for Chronos-2, suggesting that recurrent parameter sharing combined with path supervision is associated with substantially more structured predictive trajectories at a favorable accuracy-efficiency trade-off.

Related papers

• Conditional Flow Matching for ML-Based Inverse Design Problems [0.0]
  conditional flow matching (CFM) is compared with conditional diffusion model and conditional generative adversarial network (cGAN)<n>CFM produces warm starts with lower measured COG than both baselines and uses fewer network evaluations than diffusion.
  arXiv  Detail & Related papers  (2026-09-01T08:00:33Z)
• BayesSeg: A Bayesian Optimization Framework for State Segmentation of Electricity Consumption Time Series [3.3483950365040855]
  BayesSeg is a unified framework integrating time-series segmentation, multidimensional evaluation, and automatic parameter optimization.<n>The framework achieves a weighted composite score of 0.7149 and an event_F1 of 0.9340 while reducing optimization latency from 5300 seconds to under 1 second.
  arXiv  Detail & Related papers  (2026-08-01T08:22:49Z)
• FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models [65.32587991232592]
  We propose Flow Continuous Trajectory Supervision (FlowCTS)<n>FlowCTS matches subsequent student and reference trajectories from the same student-visited state.<n>Under a multi-reference setup, single-state FlowCTS-OPD outperforms vanilla KL-based OPD with faster convergence.
  arXiv  Detail & Related papers  (2026-07-27T15:03:22Z)
• Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers [68.9946633641494]
  Flow matching and Schrdinger bridges define probability, yet their inference grids are usually or inherited from one-endpoint diffusion.<n>We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution.<n>On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 pm 4.0 versus 200.5 pm 2.9 for linear and 238.0 pm 5.3 for cosine)
  arXiv  Detail & Related papers  (2026-05-15T16:11:10Z)
• N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation [68.47358899451255]
  N-vium is a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware.<n>N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits.
  arXiv  Detail & Related papers  (2026-05-13T08:46:17Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• Depth Completion as Parameter-Efficient Test-Time Adaptation [66.72360181325877]
  CAPA is a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion.<n>For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency.
  arXiv  Detail & Related papers  (2026-02-16T13:53:23Z)
• FRIREN: Beyond Trajectories -- A Spectral Lens on Time [1.5939955861266883]
  Long-term time-series forecasting models are often presented as general-purpose solutions that can be applied across domains.<n>We argue that geometric structure is the right abstraction for a dynamic-agnostic foundational model.<n>By connecting modern generative flows with classical spectral analysis, FRIREN makes long-term forecasting both accurate and interpretable.
  arXiv  Detail & Related papers  (2025-05-23T00:52:13Z)
• EMForecaster: A Deep Learning Framework for Time Series Forecasting in Wireless Networks with Distribution-Free Uncertainty Quantification [11.88654374102813]
  We develop a deep learning (DL) time series forecasting framework referred to as textitEMForecaster.<n> EMForecaster achieves superior performance across diverse datasets, spanning both short-term and long-term prediction horizons.<n>In point forecasting tasks, EMForecaster substantially outperforms current state-of-the-art DL approaches, showing improvements of 53.97% over the Transformer architecture and 38.44% over the average of all baseline models.
  arXiv  Detail & Related papers  (2025-03-31T18:10:08Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)

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.