view post Post 111 Structured financial facts, each linked to the character in the filing it came from ๐ฐ๐Today I am introducing two datasets and a model trained on them: StockAlloy/filedfact-passages A passage-complete dataset of phrases and the embedded financial facts. StockAlloy/filedfact-100kA fact-sampled version- one grounded financial fact per row, deep-linked to its source. StockAlloy/filedfact-qwen3-8bAn 8B model fine-tuned to read a filing passage and return the facts as JSON. Kroam1/filedfact-demoLive demo - paste a passage, see the facts. See translation 1 reply ยท ๐ 3 3 + Reply
MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts Paper โข 2601.21866 โข Published Jan 29 โข 1
Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers Paper โข 2601.21641 โข Published Jan 29 โข 1 โข 1
MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts Paper โข 2601.21866 โข Published Jan 29 โข 1
Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers Paper โข 2601.21641 โข Published Jan 29 โข 1
MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts Paper โข 2601.21866 โข Published Jan 29 โข 1 โข 1
Seg-MoE: Multi-Resolution Segment-wise Mixture-of-Experts for Time Series Forecasting Transformers Paper โข 2601.21641 โข Published Jan 29 โข 1