{"list":"other","total":111,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2402.11684","title":"ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models","created":"2024-02-18","cited_by_count":205},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"1910.05316","title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","created":"2019-10-04","cited_by_count":152},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2308.06735","title":"AerialVLN: Vision-and-Language Navigation for UAVs","created":"2023-08-13","cited_by_count":121},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117},{"id":"2309.04379","title":"Language Prompt for Autonomous Driving","created":"2023-09-08","cited_by_count":111},{"id":"2307.14061","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","created":"2023-07-26","cited_by_count":108},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96},{"id":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93},{"id":"2309.16739","title":"Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities","created":"2023-09-28","cited_by_count":90},{"id":"2403.02330","title":"RegionGPT: Towards Region Understanding Vision Language Model","created":"2024-03-04","cited_by_count":71},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68},{"id":"2007.15789","title":"LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy","created":"2020-07-31","cited_by_count":64},{"id":"2403.19838","title":"Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving","created":"2024-03-28","cited_by_count":52},{"id":"2012.06946","title":"MiniVLM: A Smaller and Faster Vision-Language Model","created":"2020-12-13","cited_by_count":51},{"id":"2305.10799","title":"MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts","created":"2023-05-18","cited_by_count":51},{"id":"2104.06824","title":"Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption","created":"2021-04-14","cited_by_count":48},{"id":"2304.04907","title":"Improving Vision-and-Language Navigation by Generating Future-View Image Semantics","created":"2023-04-11","cited_by_count":46},{"id":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28},{"id":"2406.15758","title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","created":"2024-06-22","cited_by_count":27},{"id":"2312.09007","title":"LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution","created":"2023-12-14","cited_by_count":24},{"id":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23},{"id":"2409.19610","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","created":"2024-09-29","cited_by_count":22},{"id":"2402.13253","title":"BiMediX: Bilingual Medical Mixture of Experts LLM","created":"2024-02-20","cited_by_count":21},{"id":"2312.01564","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","created":"2023-12-04","cited_by_count":19},{"id":"2410.10114","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","created":"2024-10-14","cited_by_count":17},{"id":"2404.15182","title":"FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning","created":"2024-04-12","cited_by_count":16},{"id":"2304.11619","title":"SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models","created":"2023-04-23","cited_by_count":15},{"id":"2404.10407","title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","created":"2024-04-16","cited_by_count":14},{"id":"2110.14895","title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing","created":"2021-10-28","cited_by_count":13},{"id":"2309.05015","title":"DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices","created":"2023-09-10","cited_by_count":13},{"id":"2410.19552","title":"GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing","created":"2024-10-25","cited_by_count":13},{"id":"2404.12467","title":"Towards Multi-modal Transformers in Federated Learning","created":"2024-04-18","cited_by_count":12},{"id":"2406.10382","title":"Efficient Prompting for LLM-based Generative Internet of Things","created":"2024-06-14","cited_by_count":12},{"id":"2406.19150","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","created":"2024-06-27","cited_by_count":10},{"id":"2306.05642","title":"Customizing General-Purpose Foundation Models for Medical Report Generation","created":"2023-06-09","cited_by_count":9}],"next_cursor":"100"}