Research map / Adversarial robustness and security / Certified and empirical robustness

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

NeurIPS 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Theory of adversarial risk

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RAD-TFM, a tabular foundation model work that designs synthetic data generators to encourage robustness and domain adaptation during TFM pretraining on synthetic datasets.

Problem

Tabular foundation models are pretrained on synthetic data, and prior work mainly focused on priors over generators; the abstract is truncated, so the full problem framing is unavailable.

Approach

Designs synthetic data generators that encourage desirable TFM properties such as robustness and domain adaptation, beyond crafting high-quality generator priors alone.

Closest papers by meaning

• Tabular Foundation Model for Generative Modelling (NeurIPS 2026 · similarity 0.89)
• TabDPT: Scaling Tabular Foundation Models on Real Data (NeurIPS 2025 · similarity 0.88)
• TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases (NeurIPS 2024 · similarity 0.87)
• Understanding the Surprising Generalization Properties of Tabular Foundation Models (NeurIPS 2026 · similarity 0.87)
• A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities (NeurIPS 2025 · similarity 0.87)
• CTSyn: A Foundation Model for Cross Tabular Data Generation (ICLR 2025 · similarity 0.86)