{"list":"other","total":53,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2304.01933","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2023-04-04","cited_by_count":324},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"1903.05485","title":"MMKG: Multi-Modal Knowledge Graphs","created":"2019-03-13","cited_by_count":105},{"id":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101},{"id":"1805.00713","title":"CrisisMMD: Multimodal Twitter Datasets from Natural Disasters","created":"2018-05-02","cited_by_count":89},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69},{"id":"2309.11206","title":"Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering","created":"2023-09-20","cited_by_count":65},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53},{"id":"2205.02357","title":"Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion","created":"2022-05-04","cited_by_count":44},{"id":"2004.04917","title":"Multimodal Categorization of Crisis Events in Social Media","created":"2020-04-10","cited_by_count":34},{"id":"2310.09036","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","created":"2023-10-13","cited_by_count":18},{"id":"2311.03783","title":"Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI","created":"2023-11-07","cited_by_count":17},{"id":"2305.08698","title":"Continual Multimodal Knowledge Graph Construction","created":"2023-05-15","cited_by_count":15},{"id":"2310.20159","title":"Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts","created":"2023-10-31","cited_by_count":14},{"id":"2408.12867","title":"Semantic Alignment for Multimodal Large Language Models","created":"2024-08-23","cited_by_count":12},{"id":"2304.02328","title":"Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck","created":"2023-04-05","cited_by_count":9},{"id":"2006.04648","title":"Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition","created":"2020-06-08","cited_by_count":6},{"id":"2003.12164","title":"Representing Multi-Robot Structure through Multimodal Graph Embedding for the Selection of Robot Teams","created":"2020-03-26","cited_by_count":1}],"next_cursor":null}