arXiv Machine Learning June 29, 2026 By Nouha Karaouli, Denis Coquenet, Elisa Fromont, Martial Mermillod, Marina Reyboz

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

Read the original on arXiv Machine Learning →

arXiv:2510. 00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 24

Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models

arXiv:2607. 20493v1 Announce Type: new Abstract: Deep learning has led to remarkable progress in artificial intelligence, particularly in robotics, imaging and sound processing.

By Quentin Besnard (RFAI), Nicolas Ragot (RFAI)

robotics benchmarks

arXiv AI

Jun 16

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

arXiv:2602. 11550v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging.

By Sisuo Lyu, Siru Zhong, Tiegang Chen, Weilin Ruan, Qingxiang Liu, Taiqiang Lv, Qingsong Wen, Raymond Chi-Wing Wong, Yuxuan Liang

efficiency benchmarks

arXiv AI

Jun 17

Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation

arXiv:2606. 18024v1 Announce Type: cross Abstract: Catastrophic forgetting in continual adaptation is usually studied through parameter drift, replay, or distillation, but these views do not identify which output-space directions are vulnerable.

By Ido Nitzan Hidekel, Dan Raviv

fine-tuning efficiency

arXiv Machine Learning

Jun 25

Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series

arXiv:2606. 24955v1 Announce Type: new Abstract: Power forecasting models deployed in real-world energy markets must operate under nonstationary conditions, where data distributions continually evolve due to weather variability, infrastructure upgrades, and changing consumption behaviors.

By Yujiang He, Frederic Uhrweiller, Bernhard Sick

arXiv AI

Jun 30

MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting

arXiv:2606. 28670v1 Announce Type: cross Abstract: We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting.

By Andrea Carriero, Davide Pettenuzzo, Shubhranshu Shekhar

fine-tuning benchmarks safety

arXiv Machine Learning

Jul 10

When Does Continual Learning Require Learning

arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?

By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai

llms agents reinforcement-learning fine-tuning efficiency benchmarks

Related stories

Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

Catastrophic Forgetting is Low-Rank: A Function-Space Theory for Continual Adaptation

Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series

MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting

When Does Continual Learning Require Learning