{"total":15,"rows":[{"id":"2510.00345","title":"Cutting the Skip: Training Residual-Free Transformers","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2508.03649","title":"Cross-Model Semantics in Representation Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.04686","title":"How does the optimizer implicitly bias the model merging loss landscape?","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2602.02016","title":"DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.27662","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.11123","title":"Overcoming Rank Collapse in Feedback Alignment","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2607.17624","title":"Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2605.04230","title":"Layerwise LQR for Geometry-Aware Optimization of Deep Networks","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2509.25637","title":"How Does Preconditioning Guide Feature Learning in Deep Neural Networks?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2604.20365","title":"Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2609.08381","title":"Equivariance Breaks the Learning Rate","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}