{"total":14,"rows":[{"id":"2410.06511","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","created":"2024-10-09","cited_by_count":85,"area":null},{"id":"2407.20143","title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2410.21316","title":"Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading","created":"2024-10-26","cited_by_count":7,"area":null},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2503.11901","title":"Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2509.03047","title":"FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2503.20507","title":"Harmonia: Enhancing Data Placement and Migration in Hybrid Storage Systems via Multi-Agent Reinforcement Learning","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2601.16956","title":"DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2505.12815","title":"Learning In Chaos: Efficient Autoscaling and Self-Healing for Multi-Party Distributed Training","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2509.02480","title":"MLP-Offload: Multi-Level, Multi-Path Offloading for LLM Pre-training to Break the GPU Memory Wall","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2605.04478","title":"CCL-D: A High-Precision Diagnostic System for Slow and Hang Anomalies in Large-Scale Model Training","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.11215","title":"ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Workload","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.07491","title":"Twelve quick tips for designing AI-driven HPC workflows","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.01646","title":"PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":null}