A Unified Framework for In-Context Learning with Causal and Masked Language Models
Chenrui Liu, Chuanlong Xie, Falong Tan, Yicheng Zeng, Lixing Zhu
cs.LG, stat.ML
Submitted: 2026-07-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Context-Scaling versus Task-Scaling in In-Context Learning
- Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
- Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers
- A survey and taxonomy of loss functions in machine learning
- Approximation Theory for Lipschitz Continuous Transformers
- When can in-context learning generalize out of task distribution?
- Automatic Domain Adaptation by Transformers in In-Context Learning
- Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought
- Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
- In-Context Learning as Nonparametric Conditional Probability Estimation: Risk Bounds and Optimality
- Optimal In-context Adaptivity and Distributional Robustness of Transformers
- On the Regularity of Attention
- In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
- Data Management For Training Large Language Models: A Survey
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks