Adapting prior-data fitted networks for tabular anomaly detection

Frozen and fine-tuned TabPFN representations for tabular anomaly detection yield ZEN and FOCUS, surpassing all ADBench baselines in AUROC despite unsupervised deployment and contaminated reference sets.

Maximilian Bershtman, Niv Cohen

Published Oct 5, 2026 · ▲ 5 on Hugging Face · Code ★ 1

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

LimiX-2 uses scaled contextual mechanism networks pretrained on synthetic causal data to outperform tabular foundation models and recover causal skeletons.

Xingxuan Zhang, Gang Ren, Hao Yuan, Hao Zou and 36 more

Published Sep 15, 2026 · 0 citations · ▲ 816 on Hugging Face · Code ★ 4,373

RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models

Matthew Peroni, Franck Le, Vadim Sheinin

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery

Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TabK: Amortized Bayesian Estimation of the Number of Clusters in Tabular Data

Mohammadreza Bakhtyari, Bogdan Mazoure, Renato C de Amorim, Guillaume Rabusseau and 1 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Semantic Priors Meet Statistical Evidence: Robust Forests for Few-Shot Tabular Learning

Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu and 1 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting

Jinlin Wang, Zhixuan Chen, Qi Ma

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

TabWorld: A World-Modeling Foundation Model for Tabular Generation

Xiaofeng Lin, Chunhe Wang, Tung Sum Thomas Kwok, Guang Cheng

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

LLM-Enhanced Random Forests in Orthogonal Hyperbolic Subspaces for Tabular Learning

Shengpeng Wang, Yisen Gao, Han Xiang, lingyun liu and 4 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Enhancing Tabular Learners with Context-Aware Semantic Embeddings

CASE contextualizes tabular embeddings via a dataset-anchored Gemma 3 language model to resolve feature semantics, substantially improving tabular learner accuracy especially with scarce data.

Günther Schindler, Maximilian Schambach, Johannes Höhne

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering

TabClustPFN is a prior-fitted network that performs amortized Bayesian clustering of tabular data in one forward pass without retraining, outperforming baseline methods.

Tianqi Zhao, Guanyang Wang, Yan Shuo Tan, Qiong Zhang

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

FlexTab uses a shared encoder and task-specific decoders for in-context tabular learning, achieving state-of-the-art results on classification, regression, anomaly detection, and entity matching.

Marek Polewczyk, Maximilian Schambach, Marco Spinaci, Sam Thelin and 1 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Understanding the Surprising Generalization Properties of Tabular Foundation Models

Self-supervised pre-training on one real table yields strong tabular transfer, where feature count predicts usefulness and in-context generalization is retrieval-based.

Nour Shaheen, Junwei (Jeremy) Ma, Alex Labach, Frank Hutter and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

STRABLE: Benchmarking Tabular Machine Learning with Strings

STRABLE introduces 108 real-world string-and-number tables and benchmarks 445 pipelines, finding simple embeddings with advanced learners suffice for categorical tables while LLMs help on free-text tables.

Gioia Blayer, Myung Jun Kim, Félix Lefebvre, Lennart Purucker and 7 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face

Embedding Foundation Model Predictions in Discrete-Choice Models with Structural Guarantees

A two-stage adapter embeds foundation model predictions into a constrained multinomial logit, guaranteeing cost monotonicity and valid value-of-time estimates while improving choice accuracy by up to 12.8 percentage points.

Yingshuo Wang, Xian Sun, Yanhang Li, Zhichao Fan and 1 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks

TabPrep is a lightweight feature engineering pipeline that targets structural data patterns to consistently boost tabular model performance across benchmarks.

Andrej Tschalzev, Nick Erickson, Yuyang (Bernie) Wang, Huzefa Rangwala and 3 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Evolutionary Feature Engineering for Structured Data

Evolutionary Feature Engineering uses LLM-based evolution to discover structured-data preprocessing transformations, reducing forecasting errors up to 19% and improving tabular predictions.

Ege Onur Taga, Yilin Zhuang, Muhammed Emrullah Ildiz, Petros Mol and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

TRL-Bench standardizes cross-paradigm evaluation of tabular encoders via shared representation-level probes, finding encoder quality is task-specific and best pipelines combine capability-matched specialists.

Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu and 9 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 10