{"list":"other","total":112,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1911.11815","title":"Local Model Poisoning Attacks to Byzantine-Robust Federated Learning","created":"2019-11-26","cited_by_count":493},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"2007.14390","title":"Flower: A Friendly Federated Learning Research Framework","created":"2020-07-28","cited_by_count":455},{"id":"2212.03860","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","created":"2022-12-07","cited_by_count":424},{"id":"1909.11875","title":"Federated Learning in Mobile Edge Networks: A Comprehensive Survey","created":"2019-09-26","cited_by_count":408},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211},{"id":"2305.20086","title":"Understanding and Mitigating Copying in Diffusion Models","created":"2023-05-31","cited_by_count":209},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187},{"id":"1910.00962","title":"Privacy-preserving Federated Brain Tumour Segmentation","created":"2019-10-02","cited_by_count":169},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"1810.04304","title":"Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation","created":"2018-10-10","cited_by_count":149},{"id":"2209.10083","title":"Federated Learning from Pre-Trained Models: A Contrastive Learning Approach","created":"2022-09-21","cited_by_count":142},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","cited_by_count":134},{"id":"2109.00984","title":"CrypTen: Secure Multi-Party Computation Meets Machine Learning","created":"2021-09-02","cited_by_count":131},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2210.09929","title":"Differentially Private Diffusion Models","created":"2022-10-18","cited_by_count":119},{"id":"2006.12097","title":"Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning","created":"2020-06-22","cited_by_count":112},{"id":"2212.05400","title":"How to Backdoor Diffusion Models?","created":"2022-12-11","cited_by_count":104},{"id":"2112.12371","title":"DENSE: Data-Free One-Shot Federated Learning","created":"2021-12-23","cited_by_count":100},{"id":"2008.12161","title":"Collaborative Fairness in Federated Learning","created":"2020-08-27","cited_by_count":95},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76},{"id":"2204.04385","title":"Divergence-aware Federated Self-Supervised Learning","created":"2022-04-09","cited_by_count":73},{"id":"2010.12797","title":"Collaborative Machine Learning with Incentive-Aware Model Rewards","created":"2020-10-24","cited_by_count":71},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71},{"id":"2210.08090","title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","created":"2022-10-14","cited_by_count":71},{"id":"2302.13485","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","created":"2023-02-27","cited_by_count":70},{"id":"2108.06492","title":"Collaborative Unsupervised Visual Representation Learning from Decentralized Data","created":"2021-08-14","cited_by_count":69},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67},{"id":"2204.05011","title":"FederatedScope: A Flexible Federated Learning Platform for Heterogeneity","created":"2022-04-11","cited_by_count":53},{"id":"2008.11560","title":"Performance Optimization for Federated Person Re-identification via Benchmark Analysis","created":"2020-08-26","cited_by_count":50},{"id":"2305.11414","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","created":"2023-05-19","cited_by_count":50},{"id":"2210.04505","title":"A Survey on Heterogeneous Federated Learning","created":"2022-10-10","cited_by_count":42},{"id":"2107.10996","title":"Communication Efficiency in Federated Learning: Achievements and Challenges","created":"2021-07-23","cited_by_count":40},{"id":"2205.10920","title":"Test-Time Robust Personalization for Federated Learning","created":"2022-05-22","cited_by_count":39},{"id":"2303.01325","title":"A Pathway Towards Responsible AI Generated Content","created":"2023-03-02","cited_by_count":38},{"id":"2202.08036","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","created":"2022-02-16","cited_by_count":37},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32},{"id":"2012.13891","title":"Federated Unlearning","created":"2020-12-27","cited_by_count":29},{"id":"2108.09412","title":"SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling","created":"2021-08-21","cited_by_count":29},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27},{"id":"2306.02210","title":"GPT-FL: Generative Pre-trained Model-Assisted Federated Learning","created":"2023-06-03","cited_by_count":24},{"id":"2206.09979","title":"Mitigating Data Heterogeneity in Federated Learning with Data Augmentation","created":"2022-06-20","cited_by_count":21},{"id":"2105.07603","title":"EasyFL: A Low-code Federated Learning Platform For Dummies","created":"2021-05-17","cited_by_count":20},{"id":"2105.13127","title":"Continual Learning at the Edge: Real-Time Training on Smartphone Devices","created":"2021-05-24","cited_by_count":20},{"id":"2108.06493","title":"Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification","created":"2021-08-14","cited_by_count":20},{"id":"2205.14926","title":"CalFAT: Calibrated Federated Adversarial Training with Label Skewness","created":"2022-05-30","cited_by_count":20},{"id":"2302.09479","title":"Delving into the Adversarial Robustness of Federated Learning","created":"2023-02-19","cited_by_count":19},{"id":"2108.13873","title":"Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs","created":"2021-08-29","cited_by_count":18},{"id":"2210.06516","title":"How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?","created":"2022-10-12","cited_by_count":17},{"id":"2303.08355","title":"Efficient and Secure Federated Learning for Financial Applications","created":"2023-03-15","cited_by_count":17},{"id":"2205.11158","title":"IDEAL: Query-Efficient Data-Free Learning from Black-box Models","created":"2022-05-23","cited_by_count":16},{"id":"2212.07224","title":"FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation","created":"2022-12-14","cited_by_count":16},{"id":"2302.06079","title":"Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting","created":"2023-02-13","cited_by_count":14}],"next_cursor":"100"}