{"total":25,"rows":[{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2503.09799","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","created":"2025-03-12","cited_by_count":27,"area":null},{"id":"2404.00438","title":"Communication Efficient Distributed Training with Distributed Lion","created":"2024-03-30","cited_by_count":18,"area":null},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"area":null},{"id":"2509.10439","title":"Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2502.04164","title":"Efficient Distributed Optimization under Heavy-Tailed Noise","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2505.01099","title":"Nesterov Method for Asynchronous Pipeline Parallel Optimization","created":"2025-05-02","cited_by_count":6,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","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":"2406.13936","title":"Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods","created":"2024-06-20","cited_by_count":4,"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":"2601.22442","title":"AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2606.22768","title":"Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2509.22418","title":"Partial Parameter Updates for Efficient Distributed Training","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2412.07210","title":"EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2504.18454","title":"Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2602.18002","title":"Asynchronous Heavy-Tailed Optimization","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2605.09126","title":"Cosine-Gated Adam-Decay: Drop-In Staleness-Aware Outer Optimization for Decoupled DiLoCo","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.24326","title":"ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.16384","title":"Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.26453","title":"Distributed Training using an Intelligent Network","created":"2026-08-26","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}