Research map / Architectures and efficiency / Attention and transformers
Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods
Zhaiming Shen, Alexander Hsu, Rongjie Lai, Wenjing Liao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train transformer on many in-context regression tasks | Transformer ICL on S^2 · Simulated spherical-harmonic regression | Pearson correlation of attention scores with Gaussian kernel: mean 0.86 (n=4) to 0.67 (n=32) | Improved |
| increase number of training tasks Gamma with fixed prompt length (ablation) | Transformer ICL · Simulated S^2 regression | test MSE | Improved |
| increase Gamma when varying prompt length n (ablation) | Transformer ICL · Simulated S^2 regression | MSE convergence rate in n | Improved |
Closest papers by meaning
- Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers (NeurIPS 2026 · similarity 0.90)
- Contextures: Representations from Contexts (ICML 2025 · similarity 0.86)
- In-Context Learning with Representations: Contextual Generalization of Trained Transformers (NeurIPS 2024 · similarity 0.86)
- Latent Functional Maps: a spectral framework for representation alignment (NeurIPS 2024 · similarity 0.85)
- The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws (NeurIPS 2026 · similarity 0.85)
- Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
