{"total":13,"rows":[{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2601.14311","title":"Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2604.00726","title":"Exploring Silent Data Corruption as a Reliability Challenge in LLM Training","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2604.22032","title":"Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2601.11864","title":"AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2601.19912","title":"Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.14462","title":"Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2608.11034","title":"SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.30769","title":"TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.19743","title":"Syndrome Decoding for Silent Data Corruption in Quantized Integer GPU Arithmetic","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}