On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

16 results for “TSFMs”

Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Modelscs.LG

Synapse arbitrates TSFMs to improve time series forecasting performance.

problem TSFMs vary in performance across different forecasting tasks, domains, and horizons.

method Synapse dynamically assigns and adjusts predictive weights based on TSFM performance.

result Synapse consistently outperforms other ensembling techniques and individual TSFMs.

Time Series Forecasting Foundational Models Adaptive Arbitration Dynamic Weighting Quantile Sampling

2025-11-07abs ↗pdf ↗

Universal Redundancies in Time Series Foundation Modelscs.LG

TSFMs show redundant components in layers, affecting their performance.

problem Redundant components in TSFMs layers impact their predictive accuracy.

method Mechanistic interpretability tools, ablations, logit attribution, theoretical framework.

result TSFMs are robust to ablations of entire layers and specific heads.

Time Series Foundation Models Redundancies Transformer Kernel Regression

2026-02-02abs ↗pdf ↗

Time Series Foundation Models for Multivariate Financial Time Series Forecastingq-fin.GN

TSFMs improve financial forecasting across diverse tasks with strong transferability.

problem Complex nonlinear relationships, temporal dependencies, and limited data in financial time series forecasting.

method Pretraining on diverse time series corpora followed by task-specific adaptation.

result Tiny Time Mixers (TTM) achieved 25-50% better performance on limited data and 15-30% improvements on longer datasets.

financial forecasting time series models transfer learning pretraining financial time series

2025-07-09abs ↗pdf ↗

Re(Visiting) Time Series Foundation Models in Financeq-fin.CP

TSFMs improve financial forecasting from diverse datasets.

problem Challenges in forecasting financial time series due to noisy, non-stationary, and heterogeneous data.

method Empirical study of TSFMs in global financial markets, evaluating zero-shot inference, fine-tuning, and pre-training from scratch.

result Pre-trained TSFMs on financial data achieve substantial forecasting and economic improvements, highlighting the value of domain-specific adaptation.

time series forecasting financial markets large language models domain adaptation hyperparameter tuning

2025-11-23abs ↗pdf ↗

Benchmarking Pre-Trained Time Series Models for Electricity Price Forecastingcs.LG

TSFMs outperform traditional models in electricity price forecasting.

problem Accurate electricity price forecasting for effective decision-making.

method Benchmarking several TSFMs against traditional models using real-world data.

result MSTL model consistently outperforms TSFMs across countries and metrics.

electricity price forecasting time series models genAI pre-trained models seasonality

2025-06-09abs ↗pdf ↗

Non-Stationarity in the Embedding Space of Time Series Foundation Modelscs.LG

TSFMs embed non-stationary time series data, revealing specific types of changes.

problem Understanding non-stationarity in TSFMs' embedding spaces.

method Examined mean shifts, variance changes, linear trends, and persistence in TSFMs.

result Different TSFMs exhibit distinct failure modes in detecting non-stationarity.

time series foundation models non-stationarity embedding space distributional shifts

2026-04-06abs ↗pdf ↗

Pretrained Time-Series Foundation Models for Financial Return Forecastingq-fin.MF

Pretrained time-series models outperform train-from-scratch baselines in financial return forecasting.

problem Financial return forecasting

method Pretrained time-series foundation models

result Pretrained TSFMs dominate the ranking distribution, accounting for 8 of 10 task-level wins.

financial return forecasting pretrained models time-series foundation models TSFMs financial markets

2026-06-25abs ↗pdf ↗

Adapting Time Series Foundation Models through Data Mixturescs.LG

MixFT re-partitions data into sub-domains for better TSFM fine-tuning.

problem Improving zero-shot forecasting for new time series domains.

method MixFT re-divides data using Bayesian mixtures into homogeneous sub-domains for separate fine-tuning.

result MixFT outperforms per-dataset fine-tuning methods.

time series forecasting zero-shot learning data mixtures sub-domains Bayesian mixtures

2026-03-03abs ↗pdf ↗

Foundation models for time series forecasting: Application in conformal predictioncs.LG

Foundation models improve time series prediction reliability, especially with limited data.

problem Improving time series prediction reliability with limited data.

method Comparison of Time Series Foundation Models (TSFMs) with traditional methods in conformal prediction.

result TSFMs provide more reliable conformalized prediction intervals and more stable calibration with limited data.

time series forecasting conformal prediction foundation models reliability limited data

2025-07-09abs ↗pdf ↗

Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecastingcs.LG

Cold-start PV forecasting uses synthetic histories to train time-series foundation models.

problem Cold-start PV forecasting

method Zero-shot pipeline with synthetic histories

result TabPFN-TS achieves the lowest error under Real Feedback strategy

cold-start PV forecasting synthetic history TSFM MAE

2026-06-05abs ↗pdf ↗

Kronos: A Foundation Model for the Language of Financial Marketsq-fin.ST

Kronos improves financial time series analysis with a pre-trained model.

problem Limited application of large-scale models to financial candlestick data.

method Unified, scalable pre-training framework for financial K-line modeling.

result Kronos excels in financial tasks like price forecasting and volatility prediction.

financial time series K-line modeling large language models volatility prediction synthetic data generation

2025-08-02abs ↗pdf ↗

Rating Multi-Modal Time-Series Forecasting Models (MM-TSFM) for Robustness Through a Causal Lenscs.LG

This paper rates robustness of multi-modal time-series forecasting models.

problem Robustness of AI systems in time-series forecasting is crucial for stakeholders.

method Causal analysis to assess robustness of MM-TSFM models.

result Multi-modal forecasting models are more robust than numeric models.

time-series forecasting robustness multi-modal causal analysis AI fragility

2024-06-12abs ↗pdf ↗

Enhancing Transformer-Based Foundation Models for Time Series Forecasting via Bagging, Boosting and Statistical Ensemblescs.LG

Enhanced TSFMs improve time series forecasting accuracy and reliability.

problem Variance, bias, and uncertainty in TSFMs' predictions on real data.

method Statistical and ensemble techniques including bagging, stacking, residual modeling, and prediction intervals.

result Hybrid models consistently outperform standalone TSFMs across multiple horizons.

time series forecasting foundation models ensemble methods statistical reasoning prediction intervals

2025-08-18abs ↗pdf ↗

ProbFM: Probabilistic Time Series Foundation Model with Uncertainty Decompositioncs.LG

ProbFM provides principled uncertainty quantification for financial forecasting.

problem Lack of principled uncertainty quantification in financial applications.

method Probabilistic Time Series Foundation Model with Uncertainty Decomposition using Deep Evidential Regression (DER).

result DER maintains competitive forecasting accuracy while providing explicit epistemic-aleatoric uncertainty decomposition.

financial forecasting uncertainty quantification Deep Evidential Regression time series foundation models

2026-01-15abs ↗pdf ↗

Forecasting Realized Volatility with Time Series Foundation Models: A Comparison with Econometric Benchmarksq-fin.ST

Foundation models improve on econometric benchmarks for forecasting volatility, but vary widely across models.

problem Comparing pretrained time series foundation models to econometric benchmarks for volatility forecasting.

method Systematic comparison of nine zero-shot TSFMs against eight econometric specifications on 50 assets across 3 markets and 3 horizons.

result Tiny Time Mixers (TTM) is the only model that consistently beats the Log-HAR benchmark, but performance varies widely across models.

volatility forecasting time series foundation models econometric benchmarks asset-specific performance foundation model architectures

2026-07-06abs ↗pdf ↗

Monitoring State Transitions in Markovian Systems with Sampling Costcs.LG

Optimizes state monitoring in Markovian systems with cost constraints.

problem Balancing state queries with prediction costs in Markovian systems.

method Greedy policy and SGD-based learning variant for optimal predict-query tradeoff.

result Greedy policy is suboptimal but performs close to optimal under certain conditions.

Markovian systems state monitoring greedy policy prediction costs time-series forecasting

2025-10-25abs ↗pdf ↗