{"list":"other","total":74,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"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":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"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":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2111.12293","title":"PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization","created":"2021-11-24","cited_by_count":179},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2105.15075","title":"Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition","created":"2021-05-31","cited_by_count":144},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"2008.06402","title":"SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud","created":"2020-08-14","cited_by_count":112},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96},{"id":"2307.12732","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","created":"2023-07-24","cited_by_count":87},{"id":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2012.03257","title":"CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices","created":"2020-12-06","cited_by_count":67},{"id":"2203.03821","title":"CF-ViT: A General Coarse-to-Fine Method for Vision Transformer","created":"2022-03-08","cited_by_count":63},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60},{"id":"1806.07840","title":"Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy","created":"2018-06-20","cited_by_count":51},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30},{"id":"2409.08250","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","created":"2024-09-12","cited_by_count":10},{"id":"2411.17662","title":"RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training","created":"2024-11-26","cited_by_count":10},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9},{"id":"2112.07133","title":"CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision","created":"2021-12-14","cited_by_count":7},{"id":"2407.15806","title":"FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones","created":"2024-07-22","cited_by_count":6},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5}],"next_cursor":null}