Today for AI
HOT RADAR
llmHEAT 6.6°

AI CLUSTERED EVENT · 10/11/2026

Huawei and ECNU Launch Qiyao Time-Series Foundation Model: Tops TIME-leaderboard and GIFT-Eval with Zero-Shot Prediction and Low-Cost Fine-Tuning

1 reports archived1 independent sourcesupdated 10/11/2026, 16:30:53
Synthesis & Latest Updates
1 Sources Cross-Validated

Huawei Cloud and East China Normal University have launched the 'Qiyao' Ascend-native time-series foundation model, which has topped the prestigious TIME-leaderboard and GIFT-Eval (Pretrained category). Deeply optimized for the Huawei Ascend ecosystem, the model offers high accuracy and robustness, supporting zero-shot prediction for scenarios like power grids and finance, while enabling low-cost fine-tuning for vertical industry customization.

LATEST/Huawei Cloud and East China Normal University have launched the 'Qiyao' Ascend-native time-series foundation model, which has topped the prestigious TIME-leaderboard and GIFT-Eval (Pretrained category). Deeply optimized for the Huawei Ascend ecosystem, the model offers high accuracy and robustness, supporting zero-shot prediction for scenarios like power grids and finance, while enabling low-cost fine-tuning for vertical industry customization.

HEAT TRENDHourly heat curve

26 fully observed hours
Now
6.6
Peak
11.917:00
24h change
-43%

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·68 pts
    • The 'Qiyao' model by Huawei Cloud and ECNU has topped both TIME-leaderboard and GIFT-Eval, two authoritative international time-series benchmarks.
    • Deeply optimized for the Ascend ecosystem, the model combines high accuracy, robustness, and ease of engineering, filling the gap for domestic general-purpose time-series foundations.
    • It supports zero-shot tasks like grid load forecasting and industrial anomaly detection, while allowing low-cost fine-tuning for rapid vertical industry adaptation.