TabPFN-3.5: Technical Report

arXiv:2609.17895 · cs.LG, stat.ML · Submitted 2026-09-15 · Read on arXiv

cs.LG, stat.ML

Submitted: 2026-09-15

Updated: 2026-09-22

Code: https://github.com/PriorLabs/TabPFN

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 51× in this paper · explained in 2 episodes
• Foundation Model — 36× in this paper · explained in 3 episodes
• Foundation Models — 19× in this paper · explained in 7 episodes
• Tabular Foundation Model — 19× in this paper
• Core — 13× in this paper · explained in 2 episodes
• Thinking mode — 9× in this paper · explained in 2 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• AUC — 5× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• In International Conference on Machine Learning — 3× in this paper
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Bayesian Optimization — 2× in this paper · explained in 3 episodes
• Time Series Forecasting — 2× in this paper · explained in 3 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Predictive Maintenance — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Shapley values — 1× in this paper · explained in 2 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Synthetic Data Generation Pipeline — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• TabPFN-3: Technical Report
• Beyond IID: How General Are Tabular Foundation Models, Really?
• STRABLE: Benchmarking Tabular Machine Learning with Strings
• Advancing Open and Reproducible Relational Learning: RelArena- alpha, TabPFN-Rel and RPI
• fev-bench: A Realistic Benchmark for Time Series Forecasting
• AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
• TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
• From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
• Do-PFN: In-Context Learning for Causal Effect Estimation
• CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
• Foundation Models for Causal Inference via Prior-Data Fitted Networks
• Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models
• Computing Conditional Shapley Values Using Tabular Foundation Models
• SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
• Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
• GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation Models
• ICR-RL: Deep Reinforcement Learning via In-Context Regression
• TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• DINOv3

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks