arXiv Machine Learning July 23, 2026 By Ahmed Cherif

Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule

Read the original on arXiv Machine Learning →

arXiv:2607. 19383v1 Announce Type: cross Abstract: Pretrained generative foundation models cast forecasting as conditional generation from a learned predictive distribution and forecast unseen series zero-shot.

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

benchmarks

arXiv Machine Learning

Jun 9

Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting

arXiv:2606. 09473v1 Announce Type: cross Abstract: Probabilistic forecasters are increasingly learned, yet the baselines they are compared against are often weak or omitted.

By Valery Manokhin

arXiv Machine Learning

Jul 15

When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecasting

arXiv:2607. 12248v1 Announce Type: cross Abstract: Large pretrained time-series models such as TimesFM are attractive for financial forecasting, but raw directional accuracy is a misleading scoreboard in equity markets.

By Taizhen Cheung, SA Kwon

fine-tuning benchmarks

arXiv AI

1d ago

Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence

arXiv:2608. 14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or expert belief.

By Fabricio F Costa

agents benchmarks safety

arXiv Machine Learning

Jul 10

Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5

arXiv:2607. 07951v1 Announce Type: new Abstract: Wildfire smoke events produce extreme PM$_{2.

By Yongcan Huang, Li Jiang, Ze Yu Liu

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 23

Expert-Guided Forecast Editing for Time-Series Foundation Models

arXiv:2607. 19659v1 Announce Type: new Abstract: Time-series foundation models can forecast across heterogeneous domains without task-specific training, but their forecasts are fixed once produced and cannot directly incorporate task-specific expert feedback.

By Hung Le, Minh Hoang Nguyen, Manh Nguyen, Huu Hiep Nguyen, Dai Do

benchmarks

arXiv AI

Jul 21

FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting

arXiv:2604. 22328v2 Announce Type: replace-cross Abstract: Driven by the transition towards a climate-neutral energy system, accurate energy time series forecasting is critical for planning and operations.

By Marco Obermeier, Marco Pruckner, Florian Haselbeck, Andreas Zeiselmair

benchmarks

Related stories

Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting

When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecasting

Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence

Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5

Expert-Guided Forecast Editing for Time-Series Foundation Models

FETS Benchmark: Foundation Models Enable Scalable and Generalizable Energy Time Series Forecasting