TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
Transformers learn in-context by gradient descent
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
PIQL integrates privileged information to accelerate convergence, lower loss, and improve generalization in tabular foundation models.
A single safety demonstration appended at inference time mitigates many-shot jailbreak attacks by counteracting implicit malicious fine-tuning on harmful examples.
A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.
citing papers explorer
-
TabQL: In-Context Q-Learning with Tabular Foundation Models
TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
-
Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
PIQL integrates privileged information to accelerate convergence, lower loss, and improve generalization in tabular foundation models.
-
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
A single safety demonstration appended at inference time mitigates many-shot jailbreak attacks by counteracting implicit malicious fine-tuning on harmful examples.
-
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.