{"total":26,"rows":[{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"area":null},{"id":"2508.15706","title":"Overcoming the Communication-Performance Tradeoff in LLM Pretraining","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2510.15830","title":"SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2506.10972","title":"Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2603.08163","title":"Covenant-72B: Pre-Training a 72B LLM with Trustless Peers Over-the-Internet","created":"2026-03-09","cited_by_count":6,"area":null},{"id":"2506.10911","title":"NoLoCo: No-all-reduce Low Communication Training Method for Large Models","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2512.17131","title":"Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2505.22549","title":"DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2604.21428","title":"Decoupled DiLoCo for Resilient Distributed Pre-training","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2507.07765","title":"Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2510.05361","title":"MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2508.17954","title":"Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2602.04396","title":"LoRDO: Distributed Low-Rank Optimization with Infrequent Communication","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.26954","title":"High dimensional theory of two-phase optimizers","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.11081","title":"Unifying Local Communications and Local Updates for LLM Pretraining","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2607.03011","title":"Can Model Merging Improve Aggregation in DiLoCo?","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.10134","title":"LeRoPE: Learnable RoPE Frequencies Improve Language Modeling","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2609.04577","title":"Optimizer Memory Schedules for Outscaling the Overtraining Axis","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2605.28585","title":"Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29359","title":"Does Distributed Training Undermine Compute Governance?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.02958","title":"Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.14731","title":"What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.05173","title":"The Closing Window: How Governments Could Lose Their Ability to Restrain Advanced AI","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.36662","title":"AutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13524","title":"Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19064","title":"How Inner Optimizers Shape Replica Scaling","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}