lqzxt/Time-R1

Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.

Language: Python - Size: 7.4 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 35 - Forks: 6

lqzxt/zotero-arxiv-daily

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Language: Python - Size: 2.7 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

lqzxt/ChemTable

ChemTable is a large-scale benchmark designed to test the capabilities of multimodal large language models (MLLMs) in understanding real-world chemical tables—one of the most information-dense and visually complex formats in scientific literature.

Language: Python - Size: 4.25 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 2 - Forks: 0

lqzxt/NGTR

Language: Python - Size: 93.7 MB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 2 - Forks: 1