mlsanityData to 14 Oct 2026

TimeHF: Billion-Scale Time Series Models Guided by Human Feedback

arXiv 2501.15942 ↗First posted 27 Jan 2025cs.LGcited by 10

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

Time series neural networks perform exceptionally well in real-world applications but encounter challenges such as limited scalability, poor generalization, and suboptimal zero-shot performance. Inspired by large language models, there is interest in developing large time series models (LTM) to address these issues. However, current methods struggle with training complexity, adapting human feedback, and achieving high predictive accuracy. We introduce TimeHF, a novel pipeline for creating LTMs with 6 billion parameters, incorporating human feedback. We use patch convolutional embedding to capture long time series information and design a human feedback mechanism called time-series policy optimization. Deployed in JD.com's supply chain, TimeHF handles automated replenishment for over 20,000 products, improving prediction accuracy by 33.21% over existing methods. This work advances LTM technology and shows significant industrial benefits.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 17 of its 22 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

17 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model29 May
  2. 2017Deep reinforcement learning from human preferences12 Jun

Other references · 15

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Segment Anythingcited by 8,234
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  6. 2024Chronos: Learning the Language of Time Seriescited by 759
  7. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  8. 2023A decoder-only foundation model for time-series forecastingcited by 692
  9. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  10. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  11. 2021Monash Time Series Forecasting Archivecited by 267
  12. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
3 more
  1. 2022Revisiting Neural Scaling Laws in Language and Visioncited by 132
  2. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 88
  3. 2024TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generationcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Modelscited by 15
  2. 2025Text Reinforcement for Multimodal Time Series Forecastingcited by 7
  3. 2026TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuningcited by 3
  4. 2026TF-CoDiT: Conditional Time Series Synthesis with Diffusion Transformers for Treasury Futurescited by 1
  5. 2026Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Modelscited by 1
  6. 2025Post-Training Corrections for Improved Time-Series Forecastingcited by 0
  7. 2025Forecast-Then-Optimize Deep Learning Methodscited by 0
  8. 2025There is No "apple" in Timeseries: Rethinking TSFM through the Lens of Invariancecited by 0
  9. 2026Enactive Artificial Intelligence: A Decision-Centric Architecture for Complex Systemscited by 0
  10. 2026Instance-Adaptive Prompts as Context for Time-Series Foundation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
  2. 2024Large Language Models for Time Series: A Survey
  3. 2025The language of time: a language model perspective on time-series foundation models
  4. 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting
  5. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
  6. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation
  7. 2025TsLLM: Augmenting LLMs for General Time Series Understanding and Prediction
  8. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model