{"total":20,"rows":[{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242,"area":null},{"id":"2410.21680","title":"Revisiting Reliability in Large-Scale Machine Learning Research Clusters","created":"2024-10-29","cited_by_count":28,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2104.09455","title":"Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs","created":"2021-04-19","cited_by_count":9,"area":null},{"id":"2108.07019","title":"Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision","created":"2021-08-16","cited_by_count":7,"area":null},{"id":"2103.00130","title":"Efficient Soft-Error Detection for Low-precision Deep Learning Recommendation Models","created":"2021-02-27","cited_by_count":4,"area":null},{"id":"2511.19468","title":"Towards a future space-based, highly scalable AI infrastructure system design","created":"2025-11-22","cited_by_count":4,"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":"2408.01391","title":"FT K-means: A High-Performance K-means on GPU with Fault Tolerance","created":"2024-08-02","cited_by_count":2,"area":null},{"id":"2411.18993","title":"Harden Deep Neural Networks Against Fault Injections Through Weight Scaling","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2605.07417","title":"Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2606.05433","title":"Zero knowledge verification for frontier AI training is possible","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2311.14062","title":"Hardware Resilience Properties of Text-Guided Image Classifiers","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2504.06531","title":"Beyond Moore's Law: Harnessing the Redshift of Generative AI with Effective Hardware-Software Co-Design","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2605.08594","title":"FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2411.19027","title":"Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2512.00059","title":"SafeCiM: Investigating Resilience of Hybrid Floating-Point Compute-in-Memory Deep Learning Accelerators","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2607.10389","title":"Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models","created":"2026-07-11","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":"2609.22991","title":"Silent Failures Beyond the 32-Bit Index Range: A Differential Characterization of Large-Tensor Matrix Multiplication in PyTorch's MPS Backend","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}