RAVEN proposes a regime-aware MoE architecture with cumulative importance thresholding and correlation-aware weighting to adaptively select temporal context for non-stationary financial forecasting.
hub
Are Transformers Effective for Time Series Forecasting?
20 Pith papers cite this work, alongside 2,619 external citations. Polarity classification is still indexing.
20
Pith papers citing it
2,619
external citations · OpenAlex
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 20representative citing papers
REST-TS resolves text collapse in multimodal time series forecasting by exclusively supervising the text branch on numerical residuals to compel genuine content extraction from text descriptions.
Proposes a matured-ground-truth TTA protocol and Frequency-Aware Calibration (FAC) that achieves competitive performance with substantially fewer parameters than prior TSF-TTA adapters.
CAST is a successor-local operator for causal forecasting of simplex-valued time series that retrieves empirical successors from causal context, stabilizes them with a persistence anchor, and applies bounded local stochastic transport while preserving the simplex by construction.
SensorFault-Bench is a new CPS-grounded benchmark showing that clean-MSE rankings of forecasting models often disagree with their robustness under standardized sensor-fault scenarios across four real datasets.
BadmintonGRF is a new public multimodal dataset and benchmark that pairs multi-view video with instrumented GRF for markerless load estimation in badminton.
AdaMamba adds input-dependent frequency bases and a unified time-frequency forgetting gate to Mamba, yielding higher forecasting accuracy than prior methods on standard long-term time series benchmarks.
PI-DLinear integrates derived thermal ODEs into DLinear to forecast AI data center power more accurately than SOTA models while respecting physical constraints under throttling and transients.
T1 uses one-to-one channel-head binding in a CNN-Transformer hybrid to achieve robust multivariate time-series imputation, cutting average MSE by 46% versus the next-best baseline across 11 datasets even at 70% missingness.
SpecReTF improves time series forecasting by retrieving similar historical patterns using windowed frequency representations with combined amplitude-phase similarity and exponential recency weighting, outperforming time-domain methods on benchmarks.
MF-Net learns a shared field state and mechanical transition rule from trajectories to deliver competitive forecasting and recoverable relation matrices on Lorenz-96 and real systems.
Optimus enables elastic decoding granularity adaptation in diffusion LLMs via chunked decoding and load-based scheduling to raise throughput under dynamic conditions.
DeRegiME uses a sparse variational GP with nonstationary regime-mixing kernel to decompose forecasts into mean, residual regimes, and noise for improved probabilistic forecasting under distribution shift.
A 0.3M-parameter patch-embedding method with a memory bank of normal patches beats Transformers and foundation models on TSB-AD univariate and multivariate anomaly detection.
StateFlow extends VARNN with dual hidden and residual-memory states plus a chunk decoder and two-stage training to enable competitive long-horizon time series forecasting while retaining a compact recurrent design.
Benchmark of 15 time-series architectures on equity portfolios finds no model dominates, with TransEnc-8 at 0.352 rank-1 acceptability and all promoted models showing negative net Sharpe at 20 bps costs under constraints.
BatteryMFormer is a multi-level Transformer that adds an aging-condition-aware decoder, meta degradation pattern memory, and dual-view encoder to forecast battery state-of-health trajectories from early operational data and outperforms baselines on four domains.
A dynamics-informed Temporal Fusion Transformer surrogate emulates stochastic tipping events in global ocean transport simulations with 465x speedup and high-fidelity timing predictions.
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
CoAD unifies outlier exposure classification and masked autoencoder reconstruction in a cooperative loop to detect subtle and prolonged time series anomalies.
citing papers explorer
-
RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
RAVEN proposes a regime-aware MoE architecture with cumulative importance thresholding and correlation-aware weighting to adaptively select temporal context for non-stationary financial forecasting.
-
Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting
REST-TS resolves text collapse in multimodal time series forecasting by exclusively supervising the text branch on numerical residuals to compel genuine content extraction from text descriptions.
-
Towards Principled Test-Time Adaptation for Time Series Forecasting
Proposes a matured-ground-truth TTA protocol and Frequency-Aware Calibration (FAC) that achieves competitive performance with substantially fewer parameters than prior TSF-TTA adapters.
-
CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Series
CAST is a successor-local operator for causal forecasting of simplex-valued time series that retrieves empirical successors from causal context, stabilizes them with a persistence anchor, and applies bounded local stochastic transport while preserving the simplex by construction.
-
Benchmarking Sensor-Fault Robustness in Forecasting
SensorFault-Bench is a new CPS-grounded benchmark showing that clean-MSE rankings of forecasting models often disagree with their robustness under standardized sensor-fault scenarios across four real datasets.
-
BadmintonGRF: A Multimodal Dataset and Benchmark for Markerless Ground Reaction Force Estimation in Badminton
BadmintonGRF is a new public multimodal dataset and benchmark that pairs multi-view video with instrumented GRF for markerless load estimation in badminton.
-
AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting
AdaMamba adds input-dependent frequency bases and a unified time-frequency forgetting gate to Mamba, yielding higher forecasting accuracy than prior methods on standard long-term time series benchmarks.
-
A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers
PI-DLinear integrates derived thermal ODEs into DLinear to forecast AI data center power more accurately than SOTA models while respecting physical constraints under throttling and transients.
-
T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation
T1 uses one-to-one channel-head binding in a CNN-Transformer hybrid to achieve robust multivariate time-series imputation, cutting average MSE by 46% versus the next-best baseline across 11 datasets even at 70% missingness.
-
Spectral Retrieval-Augmented Time-Series Forecasting
SpecReTF improves time series forecasting by retrieving similar historical patterns using windowed frequency representations with combined amplitude-phase similarity and exponential recency weighting, outperforming time-domain methods on benchmarks.
-
Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
MF-Net learns a shared field state and mechanical transition rule from trajectories to deliver competitive forecasting and recoverable relation matrices on Lorenz-96 and real systems.
-
Optimus: Elastic Decoding for Efficient Diffusion LLM Serving
Optimus enables elastic decoding granularity adaptation in diffusion LLMs via chunked decoding and load-based scheduling to raise throughput under dynamic conditions.
-
DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
DeRegiME uses a sparse variational GP with nonstationary regime-mixing kernel to decompose forecasts into mean, residual regimes, and noise for improved probabilistic forecasting under distribution shift.
-
PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection
A 0.3M-parameter patch-embedding method with a memory bank of normal patches beats Transformers and foundation models on TSB-AD univariate and multivariate anomaly detection.
-
StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting
StateFlow extends VARNN with dual hidden and residual-memory states plus a chunk decoder and two-stage training to enable competitive long-horizon time series forecasting while retaining a compact recurrent design.
-
Benchmarking Deep Time Series Models for Equity Portfolios
Benchmark of 15 time-series architectures on equity portfolios finds no model dominates, with TransEnc-8 at 0.352 rank-1 acceptability and all promoted models showing negative net Sharpe at 20 bps costs under constraints.
-
BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
BatteryMFormer is a multi-level Transformer that adds an aging-condition-aware decoder, meta degradation pattern memory, and dual-view encoder to forecast battery state-of-health trajectories from early operational data and outperforms baselines on four domains.
-
Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics
A dynamics-informed Temporal Fusion Transformer surrogate emulates stochastic tipping events in global ocean transport simulations with 465x speedup and high-fidelity timing predictions.
-
Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
-
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
CoAD unifies outlier exposure classification and masked autoencoder reconstruction in a cooperative loop to detect subtle and prolonged time series anomalies.