{"list":"other","total":63,"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"1909.07972","title":"A Joint Learning and Communications Framework for Federated Learning over Wireless Networks","created":"2019-09-17","cited_by_count":263},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129},{"id":"1709.08765","title":"Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization","created":"2017-09-26","cited_by_count":122},{"id":"1909.01865","title":"Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks","created":"2019-09-04","cited_by_count":90},{"id":"2007.07632","title":"Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis","created":"2020-07-15","cited_by_count":81},{"id":"2210.10936","title":"FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information","created":"2022-10-20","cited_by_count":58},{"id":"2111.11343","title":"Decentralized Federated Learning through Proxy Model Sharing","created":"2021-11-22","cited_by_count":57},{"id":"2107.12048","title":"Decentralized Federated Learning: Balancing Communication and Computing Costs","created":"2021-07-26","cited_by_count":55},{"id":"2407.10223","title":"On Large Language Model Continual Unlearning","created":"2024-07-14","cited_by_count":52},{"id":"2006.02499","title":"Wireless Communications for Collaborative Federated Learning","created":"2020-06-03","cited_by_count":47},{"id":"2203.10800","title":"Graph Neural Networks for Wireless Communications: From Theory to Practice","created":"2022-03-21","cited_by_count":46},{"id":"2101.03367","title":"Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems","created":"2021-01-09","cited_by_count":45},{"id":"2411.14961","title":"LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement","created":"2024-11-22","cited_by_count":38},{"id":"2312.04095","title":"Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection","created":"2023-12-07","cited_by_count":37},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35},{"id":"1906.02871","title":"Graph Embedding based Wireless Link Scheduling with Few Training Samples","created":"2019-06-07","cited_by_count":30},{"id":"2002.08569","title":"Byzantine-resilient Decentralized Stochastic Gradient Descent","created":"2020-02-20","cited_by_count":28},{"id":"2311.17474","title":"Large Language Models for Networking: Applications, Enabling Techniques, and Challenges","created":"2023-11-29","cited_by_count":28},{"id":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19},{"id":"2109.09142","title":"Decentralized Wireless Federated Learning with Differential Privacy","created":"2021-09-19","cited_by_count":18},{"id":"2104.00352","title":"Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space","created":"2021-04-01","cited_by_count":17},{"id":"2501.10062","title":"OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning","created":"2025-01-17","cited_by_count":15},{"id":"2501.15361","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","created":"2025-01-26","cited_by_count":14},{"id":"2505.12805","title":"FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA","created":"2025-05-19","cited_by_count":11},{"id":"2506.01001","title":"FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning","created":"2025-06-01","cited_by_count":10},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9},{"id":"2303.08361","title":"Towards Cooperative Federated Learning over Heterogeneous Edge/Fog Networks","created":"2023-03-15","cited_by_count":8},{"id":"2501.04436","title":"Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions","created":"2025-01-08","cited_by_count":8},{"id":"1612.00903","title":"Expander Graph and Communication-Efficient Decentralized Optimization","created":"2016-12-03","cited_by_count":7},{"id":"2310.04003","title":"The Role of Federated Learning in a Wireless World with Foundation Models","created":"2023-10-06","cited_by_count":7},{"id":"2506.12213","title":"Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation","created":"2025-06-13","cited_by_count":7},{"id":"2508.18663","title":"FFT-MoE: Efficient Federated Fine-Tuning for Foundation Models via Large-scale Sparse MoE under Heterogeneous Edge","created":"2025-08-26","cited_by_count":7},{"id":"2102.03394","title":"Network Support for High-performance Distributed Machine Learning","created":"2021-02-05","cited_by_count":4},{"id":"2110.01722","title":"Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels","created":"2021-10-04","cited_by_count":4},{"id":"2308.13269","title":"Heterogeneous Decentralized Machine Unlearning with Seed Model Distillation","created":"2023-08-25","cited_by_count":4},{"id":"2511.18291","title":"ADF-LoRA: Alternating Low-Rank Aggregation for Decentralized Federated Fine-Tuning","created":"2025-11-23","cited_by_count":4},{"id":"2505.18640","title":"ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation","created":"2025-05-24","cited_by_count":3},{"id":"2508.08278","title":"Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment","created":"2025-08-01","cited_by_count":3},{"id":"2510.17895","title":"Hierarchical Federated Unlearning for Large Language Models","created":"2025-10-19","cited_by_count":2},{"id":"2512.07536","title":"Bandwidth-Aware Network Topology Optimization for Decentralized Learning","created":"2025-12-08","cited_by_count":2},{"id":"2601.17133","title":"Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation","created":"2026-01-23","cited_by_count":2},{"id":"2602.07058","title":"SPARE: Self-distillation for PARameter-Efficient Removal","created":"2026-02-04","cited_by_count":2},{"id":"2602.20492","title":"Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA","created":"2026-02-24","cited_by_count":2},{"id":"2210.03810","title":"Gradient-Type Methods For Decentralized Optimization Problems With Polyak-{\\L}ojasiewicz Condition Over Time-Varying Networks","created":"2022-10-07","cited_by_count":1},{"id":"2505.23555","title":"Adaptive Federated LoRA in Heterogeneous Wireless Networks with Independent Sampling","created":"2025-05-29","cited_by_count":1},{"id":"2512.08443","title":"Fully Decentralized Certified Unlearning","created":"2025-12-09","cited_by_count":1},{"id":"2602.20003","title":"A Secure and Private Distributed Bayesian Federated Learning Design","created":"2026-02-23","cited_by_count":1}],"next_cursor":null}