| Transformer learns the cross-task prior and regularization for in-context learning | May 17, 2025 | In-Context Learning | —Unverified | 0 |
| Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training | Nov 25, 2024 | In-Context Learning | —Unverified | 0 |
| Transformers are Minimax Optimal Nonparametric In-Context Learners | Aug 22, 2024 | DiversityIn-Context Learning | —Unverified | 0 |
| Transformers Are Universally Consistent | May 30, 2025 | In-Context LearningLanguage Modeling | —Unverified | 0 |
| Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models | Oct 13, 2024 | In-Context LearningReinforcement Learning (RL) | —Unverified | 0 |
| Transformers for Supervised Online Continual Learning | Mar 3, 2024 | Continual LearningFew-Shot Learning | —Unverified | 0 |
| Transformers generalize differently from information stored in context vs in weights | Oct 11, 2022 | In-Context Learning | —Unverified | 0 |
| Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context | Dec 11, 2023 | In-Context Learning | —Unverified | 0 |
| Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape | Feb 2, 2024 | In-Context Learning | —Unverified | 0 |
| Transformers Learn Temporal Difference Methods for In-Context Reinforcement Learning | May 22, 2024 | In-Context LearningIn-Context Reinforcement Learning | —Unverified | 0 |