paper-with-me

홈 › Papers

VIP-COP: Context Optimization for Tabular Foundation Models

2026-05-13 · Yilong Chen, Xueying Ding, Leman Akoglu arxiv

Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specific training. However, their effectiveness is constrained by context length limits, restricting application to medium-scale data and degrading performance when inference-time data exceed pretraining size distributions. Our work introduces VIP-COP, estimating the Value of Importance for Prediction of training examples and features for hard Context OPtimization for TFMs. Its explicit selection mechanism suppresses noise and isolates influential data, enabling the model to also benefit from data augmentation by prioritizing high-value augmented samples and features. VIP-COP is (i) fast, boosting performance often within minutes of optimization, based on an online KernelSHAP-based regression with iterative refinement, value-guided context sampling, and multi-fidelity pruning; (ii) budget-aware and any-time, improving with additional test-time compute unlike heuristics that produce fixed contexts; (iii) model-aware yet fully black-box, requiring no access to model internals, making it compatible with both proprietary and open-source TFMs; (iv) interpretable, identifying discrete ``Very Important Predictors'' (samples and features) that maximize signal-to-noise, which makes it (v) robust, isolating high-value data from noise. In contrast, soft-prompt optimization requires model gradients, produces abstract latent tokens, and lacks explicit signal discrimination. Extensive experiments show that VIP-COP consistently outperforms heuristic and optimized baselines across large-scale high-dimensional testbeds, including data augmentation and data-noise settings, establishing a new state of the art in test-time context refinement for TFMs.

📄 PDF Abstract BibTeX arXiv:2605.12904

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses

2025-06-03 · Mohamed Djilani, Thibault Simonetto, Karim TIT, Florian Tambon 외

Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, their robustness to adversarial manipulation…

In-Context Learning

In-Context Learning for Latent Space Bayesian Optimization

2026-06-08 · Tuan A. Vu, Harri Lähdesmäki, Julien Martinelli arxiv

Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects such as molecules and proteins. In parallel, tabular foundation mod…

Foundation Models for Tabular Data within Systemic Contexts Need Grounding

2025-05-26 · Tassilo Klein, Johannes Hoffart

Current research on tabular foundation models often overlooks the complexities of large-scale, real-world data by treating tables as isolated entities and assuming information completeness, thereby neglecting the vital o…

Towards Unified and Data-Efficient Prognostics and Health Management with Tabular Foundation Models

2026-06-03 · Raffael Theiler, Lev Telyatnikov, Leandro Von Krannichfeldt, Olga Fink arxiv

Data-driven Prognostics and Health Management (PHM) uses time-varying condition-monitoring data to diagnose system states and estimate remaining useful life in engineered assets. These tasks are central to maintenance pl…

TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

2026-06-05 · Si-Yang Liu, Han-Jia Ye arxiv

Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated competitive performance, particularly on…