{"total":21,"rows":[{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2405.15603","title":"Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2312.05705","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2410.00131","title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2410.07192","title":"PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training","created":"2024-09-23","cited_by_count":5,"area":null},{"id":"2502.04242","title":"A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2312.00839","title":"PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction","created":"2023-12-01","cited_by_count":4,"area":null},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2507.21276","title":"LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2302.12803","title":"PiPar: Pipeline Parallelism for Collaborative Machine Learning","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2310.04649","title":"Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2601.10779","title":"Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework","created":"2026-01-15","cited_by_count":1,"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":"2409.06941","title":"FreeRide: Harvesting Bubbles in Pipeline Parallelism","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2507.04455","title":"GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models","created":"2025-07-06","cited_by_count":0,"area":null}],"next_cursor":null}