The paper studies how test‑time training (TTT) improves in‑context learning (ICL) for nonlinear models, focusing on single‑index models where features lie in a hidden low‑dimensional subspace. By applying TTT to single‑layer transformers trained with gradient‑based methods, the authors derive an upper bound on prediction risk and show that TTT allows the model to adapt to both feature vectors and link functions that vary across tasks—something ICL alone struggles to achieve. They also provide a convergence rate indicating that predictive error can approach the noise level as context size and network width increase.
arXiv:2607. 00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning.
Transformers can learn broad families of tasks during pretraining and adapt to unseen tasks from a short prompt, but a rigorous understanding of this capability is limited. This paper studies how shared cross‑task structure influences the sample complexity of in‑context learning (ICL) by characterizing task‑space complexity through covering numbers, yielding a set of anchor functions that localize unseen tasks and predict responses. The authors construct a Transformer with Softmax attention to approximate this procedure and derive an error bound that separates the effects of pretraining tasks and prompt length, showing that once enough tasks are available the dependence on prompt length becomes dimension‑free.
arXiv:2610.01712v1 Announce Type: cross Abstract: In-context learning (ICL) enables a pretrained model to infer a task from demonstrations without updating its parameters. While much of the existing...
arXiv:2506. 05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention.
arXiv:2609.36448v1 Announce Type: new Abstract: Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. Ho...
arXiv:2608. 01672v1 Announce Type: cross Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later.
arXiv:2607. 03660v1 Announce Type: cross Abstract: Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt.
arXiv:2606. 15569v1 Announce Type: new Abstract: Test-time training (TTT) adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
arXiv:2607. 15819v1 Announce Type: cross Abstract: In-context learning is a remarkable property of transformers and has recently received a lot of interest.
The paper introduces Decision Titan, a variant of the Decision Transformer that incorporates Test‑Time Training (TTT) layers to store episodic memories in network parameters. It evaluates this architecture on the X‑Maze environment, showing that Decision Titan can learn long‑term dependencies up to 20 times longer than its context window and generalise to sequences 1.7 times longer than the training data. The study also finds that temporal generalisation depends on the choice of time embeddings and that the ability to learn long‑term dependencies hinges on how relevant information is encoded.
arXiv:2606. 25342v1 Announce Type: new Abstract: Lifelong continual learning remains an obstacle on the path to human-like intelligence.
arXiv:2606. 06814v1 Announce Type: cross Abstract: The transformer's emergent ability to perform in-context learning (ICL) has sparked a wide range of studies designed to understand its underlying mechanisms.