{"total":13,"rows":[{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"area":null},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50,"area":null},{"id":"2502.06857","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","created":"2025-02-07","cited_by_count":20,"area":null},{"id":"2111.04949","title":"A Survey and Empirical Evaluation of Parallel Deep Learning Frameworks","created":"2021-11-09","cited_by_count":7,"area":null},{"id":"2502.08145","title":"Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2302.05045","title":"Exploiting Sparsity in Pruned Neural Networks to Optimize Large Model Training","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2511.09557","title":"Understanding and Improving Communication Performance in Multi-node LLM Inference","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2402.07901","title":"FAST: Factorizable Attention for Speeding up Transformers","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2505.04083","title":"Plexus: Taming Billion-edge Graphs with 3D Parallel Full-graph GNN Training","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2506.05300","title":"Power Law Guided Dynamic Sifting for Efficient Attention","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2504.18658","title":"The Big Send-off: Scalable and Performant Collectives for Deep Learning","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2604.02651","title":"Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2605.08633","title":"Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction","created":"2026-05-09","cited_by_count":0,"area":null}],"next_cursor":null}