{"total":16,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"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":"2405.15362","title":"Pipeline Parallelism with Controllable Memory","created":"2024-05-24","cited_by_count":11,"area":null},{"id":"2411.09510","title":"Communication Compression for Tensor Parallel LLM Inference","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2301.08984","title":"SuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction","created":"2023-01-21","cited_by_count":5,"area":null},{"id":"2312.03549","title":"Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2403.07585","title":"Communication Optimization for Distributed Training: Architecture, Advances, and Opportunities","created":"2024-03-12","cited_by_count":3,"area":null},{"id":"2311.15269","title":"Tessel: Boosting Distributed Execution of Large DNN Models via Flexible Schedule Search","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2401.01728","title":"Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2601.09026","title":"Layer-Parallel Training for Transformers","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2403.11204","title":"Partitioned Neural Network Training via Synthetic Intermediate Labels","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2507.05829","title":"Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.19855","title":"CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2410.00173","title":"GaNDLF-Synth: A Framework to Democratize Generative AI for (Bio)Medical Imaging","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2510.08874","title":"Slicing Is All You Need: Towards A Universal One-Sided Algorithm for Distributed Matrix Multiplication","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null}],"next_cursor":null}