{"list":"other","total":91,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18628},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17629},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":16029},{"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":6146},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5539},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4398},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4330},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3919},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2883},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2728},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2659},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2507},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2435},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2150},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1926},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1665},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1299},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1248},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1197},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1123},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1091},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1070},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1043},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":950},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":784},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":669},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":625},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":619},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":604},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":567},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":544},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":538},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":532},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"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":513},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":481},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":461},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":336},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"1702.01992","title":"Gated Multimodal Units for Information Fusion","created":"2017-02-07","cited_by_count":249},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":228},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":218},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":205},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":159},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":133},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2110.12951","title":"Seeing biodiversity: perspectives in machine learning for wildlife conservation","created":"2021-10-25","cited_by_count":130},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102},{"id":"2209.06293","title":"Do Androids Laugh at Electric Sheep? Humor \"Understanding\" Benchmarks from The New Yorker Caption Contest","created":"2022-09-13","cited_by_count":98},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":93},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83},{"id":"2311.05332","title":"On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving","created":"2023-11-09","cited_by_count":80},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46},{"id":"1810.13348","title":"Multimodal Machine Learning for Automated ICD Coding","created":"2018-10-31","cited_by_count":41},{"id":"2310.19061","title":"Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V","created":"2023-10-29","cited_by_count":38},{"id":"1904.09073","title":"Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts","created":"2019-04-19","cited_by_count":37},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31},{"id":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31},{"id":"2303.15445","title":"IRFL: Image Recognition of Figurative Language","created":"2023-03-27","cited_by_count":23},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18},{"id":"1506.06833","title":"A Survey of Current Datasets for Vision and Language Research","created":"2015-06-23","cited_by_count":13},{"id":"2310.02569","title":"ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks","created":"2023-10-04","cited_by_count":12},{"id":"1906.08595","title":"Understanding, Categorizing and Predicting Semantic Image-Text Relations","created":"2019-06-20","cited_by_count":4}],"next_cursor":null}