arXiv AI
Aug 12
TACTICL: Task-Aware Compression of Tabular ICL Models
arXiv:2608. 10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs.
LoopICL: Looping a single transformer block to solve tabular tasks
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.
Related stories
arXiv Machine Learning
Sep 17
TabICLv2: A better, faster, scalable, and open tabular foundation model
TabICLv2 is a new state‑of‑the‑art tabular foundation model that outperforms existing methods on regression and classification tasks. It relies on a synthetic data generation engine for diverse pretraining, architectural innovations such as a scalable softmax attention, and optimized training protocols that replace AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 surpasses the current best model, RealTabPFN‑2.5, without any tuning, while also being faster and capable of handling million‑scale datasets with limited GPU memory.
arXiv Machine Learning
Aug 4
TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
arXiv:2608. 01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity.
arXiv Machine Learning
Aug 24
Tydra: An Efficient Hybrid Model for Tabular Data
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 Machine Learning
Jun 8
TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
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.
arXiv Machine Learning
2d ago
Benchmarking Attention for Tabular Foundation Models
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.
arXiv Machine Learning
Sep 22
Causilo Technical Report
Causilo is a new tabular foundation model that delivers state‑of‑the‑art predictive performance while achieving exceptionally fast inference. On the TabArena benchmark it scores 1785.4 Elo with a median inference time of 0.10 seconds per 1 K test samples, outperforming TabPFN‑3.5‑Fast by 31.6% in speed and reaching the performance–efficiency Pareto frontier. The architecture builds on TabICL’s column‑then‑row design, adding a row‑refinement module that exchanges information among cell representations before a final column stage, and uses cross‑attention with a fixed number of summary tokens to keep attention cost linear in the number of features.
arXiv Machine Learning
Aug 18
Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN
arXiv:2608. 16429v1 Announce Type: new Abstract: Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tabular classification tasks.
arXiv Machine Learning
Jun 2
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
arXiv:2606. 02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures.
arXiv Machine Learning
Aug 31
SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning
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.
arXiv Machine Learning
1d ago
Looped Transformers as Optimizers
arXiv:2609.37379v1 Announce Type: new Abstract: Looped Transformers provide a parameter-efficient approach to depth scaling by repeatedly applying shared Transformer blocks. Recent reasoning models h...
arXiv Machine Learning
Sep 24
Support-Compiled Feature Folding: More Evidence at Lower Memory Across Tabular Foundation Models
Support-Compiled Feature Folding (SCFF) is a training‑free inference framework that addresses the feature‑side scaling dilemma in tabular foundation models by routing support‑ranked features through bounded leaves of the native encoder, checking residual evidence, and merging encoded messages for a single contextual prediction. This approach transforms quadratic pairwise mixing into linear‑in‑width work with a bounded local working set, achieving dataset‑macro accuracy and NLL improvements across six backbones on an 18‑dataset wide‑table slice. SCFF delivers significant GPU‑memory savings (median 2.09×–2.36×) and, when constrained by a peak‑memory ceiling, further boosts accuracy by up to 4.06 points over the widest single‑leaf baseline. whyItMatters":"SCFF demonstrates that memory‑efficient inference can simultaneously improve accuracy and reduce resource usage in tabular foundation models, offering a practical solution for deploying these models at scale."