| Jul 26, 2026 | Three-Layer Learning as a DMFT–RMT–BBP Closure Problem |
| Jul 22, 2026 | Three Layers, One Hierarchy: From Exact Hermite Dynamics to DMFT and BBP |
| Jul 22, 2026 | Does Muon Help a Hierarchical Three-Layer Model? |
| Jul 14, 2026 | When Both Layers Learn: Where Hessian Outliers Come From |
| Jul 14, 2026 | Beyond Quadratic Phase Retrieval: Spectral Learning with General Gaussian Links |
| Jul 06, 2026 | transformers for inverse problems on PDEs, Part 6: How Attention Learns a Preconditioner |
| Jul 06, 2026 | Muon for Phase Retrieval III: What Is Proved and What Remains Open |
| Jun 23, 2026 | transformers for inverse problems on PDEs, Part 5: Separating Encoder, Decoder, and Generalization Error |
| Jun 14, 2026 | Muon for Phase Retrieval II: Choosing the Power During Training |
| Jun 10, 2026 | transformers for inverse problems on PDEs, Part 4: What Can Be Proved About the Solver? |
| May 27, 2026 | transformers for inverse problems on PDEs, Part 3: Turning PDE Solutions Into Transformer Tokens |
| May 23, 2026 | When Does the Hessian Reveal a Hidden Direction? |
| May 14, 2026 | transformers for inverse problems on PDEs, Part 2: Inferring Unknown PDE Coefficients From Examples |
| May 01, 2026 | Muon for Phase Retrieval I: Learning Hidden Directions with One Fixed Power |
| May 01, 2026 | transformers for inverse problems on PDEs, Part 1: Solving Many PDE Inputs With One Learned Decoder |