Mitra-v2: Scaling synthetic pretraining for tabular foundation models
Imported from official source
Expanding the mix of synthetic data used to train a tabular foundation model enables it to adapt to new tables without new models and lead the single-model field on the TabArena benchmark.
This version
- Version
- 1 of 1
- Recorded
- November 10, 2026 16:00
- Change
- Initial
- Content hash
66a1aa1df579eb4541e3904f2df92670- All versions
- Revision history