{"total":18,"rows":[{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2509.03018","title":"Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2604.09107","title":"TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training","created":"2026-04-10","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":"2512.22492","title":"Role-Based Fault Tolerance System for LLM RL Post-Training","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2412.12636","title":"TrainMover: An Interruption-Resilient Runtime for ML Training","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2609.34645","title":"Nereus: Adaptive Parallelism for LLM Post-Training","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2503.01066","title":"Alchemist: Towards the Design of Efficient Online Continual Learning System","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2507.12619","title":"BootSeer: Analyzing and Mitigating Initialization Bottlenecks in Large-Scale LLM Training","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2604.17104","title":"TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.09370","title":"From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.17821","title":"TierCheck: Tiered Checkpointing for Fault Tolerance in Large Language Model Training","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.23066","title":"Orbax: Distributed Checkpointing with JAX","created":"2026-05-21","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},{"id":"2609.19924","title":"The Life of a Token: from Words to Bits on the Wire","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.00687","title":"Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03087","title":"Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}