MatrixFormer：面向矩阵补全的基础模型
MatrixFormer: A Foundation Model for Matrix Completion
团队训练了一个专做矩阵补全的 Transformer，一次前向就能补全整块缺失数据，零样本用在推荐、表格插补和因果推断上都行，思路和 TabPFN 这类逐条预测的表格模型不一样。
MatrixFormer 是一个矩阵原生的预训练 Transformer，能在单次前向传播中为每个缺失条目预测完整分布，而不是像现有表格基础模型那样逐条预测并重复上下文。模型完全基于合成低秩矩阵和潜在因子矩阵训练，覆盖多种缺失模式。以零样本方式、使用同一套权重，MatrixFormer 在因果推断面板数据任务、语言模型基准分数补全、表格插补和推荐系统矩阵补全上取得有竞争力的表现。
MatrixFormer: A Foundation Model for Matrix Completion
Matrix completion underlies problems from tabular imputation to causal inference, yet existing tabular foundation models treat it as entry-by-entry prediction, repeating context for every target and discarding the matrix's two-dimensional structure. We introduce MatrixFormer, a pre-trained matrix-native transformer that predicts a full distribution for every missing entry in a single forward pass. MatrixFormer is trained entirely on synthetic low-rank and latent-factor matrices under diverse missingness patterns. Applied zero-shot and with the same model weights, MatrixFormer achieves competitive performance on causal inference panel-data tasks, language-model benchmark-score completion, tabular imputation, and recommendation systems matrix completion. These results position MatrixFormer as a general-purpose foundation model for matrix completion.