Chenjuan Guo

Forget relying solely on numbers: VoT unlocks richer time series forecasts by fusing LLM reasoning over event-related text with multi-level data alignment.

By explicitly aligning the graph structures of predicted and actual time series correlations, GCGNet achieves superior forecasting accuracy in noisy, real-world datasets compared to methods that model temporal and channel dependencies separately.

LLMs can now better understand time series data by explicitly modeling trends and seasonality, leading to improved question answering performance.

Forget static agent communication structures: ST-EVO dynamically reshapes multi-agent dialogue flows in both space and time, boosting accuracy by up to 25%.