{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","cited_by_count":352},{"id":"2206.03382","title":"Tutel: Adaptive Mixture-of-Experts at Scale","created":"2022-06-07","cited_by_count":201},{"id":"2112.00059","title":"Evaluating Gradient Inversion Attacks and Defenses in Federated Learning","created":"2021-11-30","cited_by_count":196},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2007.05558","title":"The Computational Limits of Deep Learning","created":"2020-07-10","cited_by_count":193},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2209.01188","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","created":"2022-09-02","cited_by_count":87},{"id":"2406.17706","title":"FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model","created":"2024-06-25","cited_by_count":74},{"id":"2211.01452","title":"MPCFormer: fast, performant and private Transformer inference with MPC","created":"2022-11-02","cited_by_count":69},{"id":"2206.00216","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","created":"2022-06-01","cited_by_count":57},{"id":"2310.05077","title":"FedFed: Feature Distillation against Data Heterogeneity in Federated Learning","created":"2023-10-08","cited_by_count":54},{"id":"2104.10949","title":"CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU","created":"2021-04-22","cited_by_count":46},{"id":"2202.06924","title":"Do Gradient Inversion Attacks Make Federated Learning Unsafe?","created":"2022-02-14","cited_by_count":44},{"id":"2107.01154","title":"Gradient-Leakage Resilient Federated Learning","created":"2021-07-02","cited_by_count":40},{"id":"2206.07284","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","created":"2022-06-15","cited_by_count":40},{"id":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39},{"id":"2401.08383","title":"Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference","created":"2024-01-16","cited_by_count":28},{"id":"2501.10714","title":"FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models","created":"2025-01-18","cited_by_count":17},{"id":"2405.15586","title":"DAGER: Exact Gradient Inversion for Large Language Models","created":"2024-05-24","cited_by_count":14},{"id":"2411.19128","title":"Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures","created":"2024-11-28","cited_by_count":12},{"id":"2404.11121","title":"TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment","created":"2024-04-17","cited_by_count":11},{"id":"2410.20380","title":"FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion","created":"2024-10-27","cited_by_count":11},{"id":"2403.14772","title":"Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures","created":"2024-03-21","cited_by_count":8},{"id":"2407.00599","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","created":"2024-06-30","cited_by_count":7},{"id":"2502.04411","title":"Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing","created":"2025-02-06","cited_by_count":7},{"id":"2204.12495","title":"Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies","created":"2022-04-26","cited_by_count":5},{"id":"2306.06399","title":"Personalized Graph Federated Learning with Differential Privacy","created":"2023-06-10","cited_by_count":4},{"id":"2406.00999","title":"Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients","created":"2024-06-03","cited_by_count":3}],"next_cursor":null}