{"total":18,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660,"area":null},{"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":"2306.10209","title":"ZeRO++: Extremely Efficient Collective Communication for Giant Model Training","created":"2023-06-16","cited_by_count":52,"area":null},{"id":"2309.10285","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","created":"2023-09-19","cited_by_count":17,"area":null},{"id":"2311.10418","title":"DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines","created":"2023-11-17","cited_by_count":12,"area":null},{"id":"2302.08005","title":"Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2311.11822","title":"Zero redundancy distributed learning with differential privacy","created":"2023-11-20","cited_by_count":7,"area":null},{"id":"2403.00877","title":"Disaggregated Multi-Tower: Topology-aware Modeling Technique for Efficient Large-Scale Recommendation","created":"2024-03-01","cited_by_count":6,"area":null},{"id":"2407.12117","title":"MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2402.15514","title":"Large Scale Generative AI Text Applied to Sports and Music","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2506.21263","title":"DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2408.01000","title":"Adaptive Two-Stage Cloud Resource Scaling via Hierarchical Multi-Indicator Forecasting and Bayesian Decision-Making","created":"2024-08-02","cited_by_count":2,"area":null},{"id":"2303.04759","title":"RAF: Holistic Compilation for Deep Learning Model Training","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2311.05034","title":"Just-in-time Quantization with Processing-In-Memory for Efficient ML Training","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2403.08837","title":"Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2501.04266","title":"Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2604.24013","title":"CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training","created":"2026-04-27","cited_by_count":0,"area":null}],"next_cursor":null}