{"list":"other","total":54,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"2110.14795","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","created":"2021-10-27","cited_by_count":690},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2204.09817","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","created":"2022-04-21","cited_by_count":339},{"id":"2102.10662","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","created":"2021-02-21","cited_by_count":320},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2402.11574","title":"Visual In-Context Learning for Large Vision-Language Models","created":"2024-02-18","cited_by_count":128},{"id":"2107.00781","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","created":"2021-07-02","cited_by_count":116},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115},{"id":"2103.05940","title":"TransMed: Transformers Advance Multi-modal Medical Image Classification","created":"2021-03-10","cited_by_count":86},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39},{"id":"2401.02013","title":"SwitchTab: Switched Autoencoders Are Effective Tabular Learners","created":"2024-01-04","cited_by_count":38},{"id":"2304.03262","title":"When do you need Chain-of-Thought Prompting for ChatGPT?","created":"2023-04-06","cited_by_count":35},{"id":"2308.08333","title":"Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN","created":"2023-08-16","cited_by_count":35},{"id":"2307.01981","title":"A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosis","created":"2023-07-05","cited_by_count":31},{"id":"2305.08776","title":"Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models","created":"2023-05-15","cited_by_count":27},{"id":"2403.12776","title":"Automated Data Curation for Robust Language Model Fine-Tuning","created":"2024-03-19","cited_by_count":27},{"id":"2310.18541","title":"ReConTab: Regularized Contrastive Representation Learning for Tabular Data","created":"2023-10-28","cited_by_count":25},{"id":"2403.13335","title":"Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection","created":"2024-03-20","cited_by_count":22},{"id":"2204.10394","title":"Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations","created":"2022-04-21","cited_by_count":20},{"id":"2206.02082","title":"Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval","created":"2022-06-05","cited_by_count":16},{"id":"2303.02460","title":"Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis","created":"2023-03-04","cited_by_count":14},{"id":"2209.09991","title":"Optimizing Crop Management with Reinforcement Learning and Imitation Learning","created":"2022-09-20","cited_by_count":13},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","cited_by_count":8},{"id":"2305.14449","title":"Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding","created":"2023-05-23","cited_by_count":8},{"id":"2307.14612","title":"GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing","created":"2023-07-27","cited_by_count":8},{"id":"2312.01619","title":"How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking","created":"2023-12-04","cited_by_count":8}],"next_cursor":null}