{"total":14,"rows":[{"id":"2211.06934","title":"TorchOpt: An Efficient Library for Differentiable Optimization","created":"2022-11-13","cited_by_count":17,"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":"2305.13854","title":"The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2112.01349","title":"MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment","created":"2021-12-02","cited_by_count":13,"area":null},{"id":"2305.10863","title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2209.06018","title":"An Analysis of Collocation on GPUs for Deep Learning Training","created":"2022-09-13","cited_by_count":6,"area":null},{"id":"2108.11826","title":"Fast and Flexible Human Pose Estimation with HyperPose","created":"2021-08-26","cited_by_count":5,"area":null},{"id":"2310.05205","title":"GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2409.18749","title":"TensorSocket: Shared Data Loading for Deep Learning Training","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2110.07029","title":"Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2502.06581","title":"A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2205.14465","title":"ByteComp: Revisiting Gradient Compression in Distributed Training","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2304.08925","title":"Understand Data Preprocessing for Effective End-to-End Training of Deep Neural Networks","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2512.10980","title":"Reducing Fragmentation and Starvation in GPU Clusters through Dynamic Multi-Objective Scheduling","created":"2025-12-04","cited_by_count":0,"area":null}],"next_cursor":null}