mlsanityData to 14 Oct 2026

TIMBRE: Teaching Time Series Forecasters to Read, Remember, and Reconcile

arXiv 2610.04795 ↗First posted 3 Oct 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Event-informed forecasting requires translating reports and historical responses into changes to a numerical forecast. We propose TIMBRE (Temporal Integration of Memory-Based Responses and Evidence), which combines source-aware representation, state-conditioned response transfer, and reliability-guided fusion before a frozen forecast head. A separate readout adjusts interval widths while preserving the median. In a single-seed, one-epoch development study of 13 tasks, TIMBRE improves MAE over ordinary fusion on eight tasks but over native Chronos-2 on only two. Disabling response transfer in the trained model reduces BTC and AULF MAE by 47.04% and 6.81%, respectively. These findings identify sensitivity to learned response transfer rather than a general forecasting advantage. Missing development-set scores and the absence of retrained ablations limit attribution to individual evidence mechanisms.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 3 Oct 2026.

Builds on

22 of 27 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2018Self-Attention with Relative Position Representationscited by 1,120
  6. 2024Chronos: Learning the Language of Time Seriescited by 759
  7. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  8. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  9. 2023A decoder-only foundation model for time-series forecastingcited by 692
  10. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  11. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  12. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
10 more
  1. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  2. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
  3. 2025Chronos-2: From Univariate to Universal Forecastingcited by 194
  4. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  5. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
  6. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 98
  7. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 74
  8. 2025Improving Time Series Forecasting via Instance-aware Post-hoc Revisioncited by 15
  9. 2026Overcoming the Modality Gap in Context-Aided Forecastingcited by 5
  10. 2026Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecastingcited by 3

Built on by

Not cited yet.