Tydra is a hybrid Transformer‑State Space Model that interleaves attention and SSM layers for tabular in‑context learning. It achieves a 30% reduction in inference time compared to the Transformer‑only TabPFN while preserving most of its predictive performance. On 30 OpenML datasets, Tydra also outperforms a Hydra model that is roughly ten times larger, demonstrating that hybrid architectures can balance accuracy and efficiency for tabular foundation models.
arXiv:2608. 01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity.
arXiv:2606. 07345v1 Announce Type: new Abstract: Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples.
SOMTab is a Set-Order Mamba architecture designed for efficient tabular in-context learning. It separates representation construction from query-conditioned retrieval, using Mamba-based state‑space mixing to build compact row and column representations while retaining attention for final prediction. The model, along with a synthetic prior called DCH‑TailMix, achieves performance comparable to Transformer‑based tabular foundation models but with faster inference and lower GPU memory usage.
The paper shows that Tabular Foundation Models (TFMs) are highly overparameterized, with up to 96% of transformer blocks removable without significant loss in performance. Using a closed‑form, label‑free affine translator, the authors demonstrate that halving the depth of eight leading TFMs costs at most $0.002$ median AUROC, while a single‑block TabPFN‑3 remains competitive. Removing depth saves up to 1.5 B parameters, speeds GPU inference up to 6×, and reduces memory usage by 6× with negligible accuracy loss.
The paper introduces a reproducible benchmark for evaluating attention mechanisms in tabular foundation models, focusing on the distinct row and column attention patterns that differ from language model attention. It compares several backends—Torch SDPA, FlashAttention variants, vLLM, and SageAttention—across realistic tabular shapes on A100, H100, and B200 GPUs, revealing that optimal backend choice varies by attention type, hardware, and model specifics. The study finds FlashAttention generally performs best, but CuDNN can outperform it for column attention on longer sequences, while SageAttention excels for large row sequences beyond 16k rows.
The paper investigates how test‑time compute techniques—adaptation, aggregation, and context construction—can improve predictions of pretrained tabular foundation models (TFMs). It introduces DiagScale, a lightweight adaptation method that trains a minuscule fraction of parameters yet matches full fine‑tuning gains, and shows that selective aggregation of predictions from diverse preprocessing variants can reduce error, while broader context expansion offers inconsistent benefits. The study concludes that adaptation and selective aggregation consistently yield benchmark‑level improvements, but their combined use demands more computation, guiding strategy selection based on available resources.
arXiv:2608. 10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs.
OrionMoE-v1.0 is a compact tabular foundation model that uses a dual‑axis Transformer and a sparse mixture‑of‑experts architecture to perform in‑context learning on labeled support tables. It selectively activates experts along the feature axis, guided by both individual feature representations and overall dataset context, enabling adaptive computation across diverse tabular problems. Pretrained on synthetic classification tasks, it achieves competitive performance on multiple benchmarks, especially on small‑context, high‑dimensional, and class‑imbalanced datasets.
arXiv:2607. 27546v1 Announce Type: new Abstract: Tabular Foundation Models, such as TabPFN, have received a large amount of recent attention due to their performance on in-context tabular machine learning tasks, which often exceeds classical baselines.
The study shows that tabular foundation models (TFMs) can be dramatically simplified without losing performance. By replacing up to 96% of transformer blocks with a label‑free affine translator, researchers found that half‑depth models still outperform full‑depth TFMs and tuned GBDTs across 171 classification datasets. The simplification reduces parameters by up to 1.5 B, speeds GPU inference up to 6×, and cuts memory usage by 6× with minimal impact on AUROC.
LoopICL is a transformer architecture that loops a single block to address tabular tasks. It separates parameter count from computational depth by using a cell stream for per‑cell features and a row stream for in‑context examples, refined via within‑column and cross‑column attention. During pre‑training, varying loop counts and a learned exit‑gate allow the model to adjust inference depth at test time, achieving competitive performance with TabICLv2 while using about 90% fewer parameters.
arXiv:2608. 12989v1 Announce Type: new Abstract: Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context.