← Back to Model Beat
Open Source·Sep 4·all news from September 4, 2026

Xiaomi-TabLDM: A Tabular Foundation Model Technical Report

Xiaomi-TabLDM is a new foundation model designed to perform classification and regression tasks on tabular data using in-context learning. By training on synthetic datasets, the model aims to achieve high prediction accuracy without the need for task-specific fine-tuning.

Covered by 1 source

  • AarXiv CS.AITabLDM Team, Penghui Wang, Wei Liu, Hong Wang, Chengyue Huang, Yuxi Sun, Zirui Wang, Hongming Huang, Quan Wang, Chunxiao Liu, Erli Meng, Bin WangSep 4

Related stories

Open SourceA.X K2 Technical ReportSep 1Open SourceMitra-v2 Technical ReportSep 7Open SourceRetinal OCTA Phenotyping with LLM Reporting for Alzheimer's DiseaseSep 7Open SourceAccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident ReportsSep 7