{"total":16,"rows":[{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2510.24626","title":"Relative Scaling Laws for LLMs","created":"2025-10-28","cited_by_count":6,"area":null},{"id":"2510.13859","title":"Benchmarking Correctness and Security in Multi-Turn Code Generation","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2608.15062","title":"Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation","created":"2026-08-15","cited_by_count":4,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2605.27989","title":"The Model Shape Behind Scaling Laws: A Gradient Superposition Perspective","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.13929","title":"VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.35707","title":"ScAn-Bench: Evaluating Scaling Analysis Methodology","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16297","title":"SLDBench v2: Active Scaling Law Discovery","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}