{"list":"other","total":57,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273},{"id":"2012.05876","title":"Neurosymbolic AI: The 3rd Wave","created":"2020-12-10","cited_by_count":255},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2308.15560","title":"WeatherBench 2: A benchmark for the next generation of data-driven global weather models","created":"2023-08-29","cited_by_count":236},{"id":"2303.11408","title":"Stable Bias: Analyzing Societal Representations in Diffusion Models","created":"2023-03-20","cited_by_count":226},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178},{"id":"2304.02948","title":"FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead","created":"2023-04-06","cited_by_count":175},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159},{"id":"2008.06388","title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","created":"2020-08-14","cited_by_count":158},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153},{"id":"2011.09926","title":"Challenges in Deploying Machine Learning: a Survey of Case Studies","created":"2020-11-18","cited_by_count":152},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"1901.04407","title":"Self-Driving Cars: A Survey","created":"2019-01-14","cited_by_count":148},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146},{"id":"2205.02302","title":"Machine Learning Operations (MLOps): Overview, Definition, and Architecture","created":"2022-05-04","cited_by_count":128},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"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":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106},{"id":"2405.01147","title":"Why Tabular Foundation Models Should Be a Research Priority","created":"2024-05-02","cited_by_count":106},{"id":"2304.07993","title":"In-Context Operator Learning with Data Prompts for Differential Equation Problems","created":"2023-04-17","cited_by_count":101},{"id":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92},{"id":"1804.11238","title":"Privacy Preserving Machine Learning: Threats and Solutions","created":"2018-03-27","cited_by_count":79},{"id":"2410.13638","title":"Scaling Wearable Foundation Models","created":"2024-10-17","cited_by_count":63},{"id":"2309.12325","title":"FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare","created":"2023-08-11","cited_by_count":60},{"id":"2012.13294","title":"Multi-fidelity Bayesian Neural Networks: Algorithms and Applications","created":"2020-12-19","cited_by_count":59},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2401.14484","title":"Design Principles for Generative AI Applications","created":"2024-01-25","cited_by_count":57},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54},{"id":"2401.09646","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","created":"2024-01-17","cited_by_count":47},{"id":"1807.00123","title":"Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities","created":"2018-06-30","cited_by_count":43},{"id":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31},{"id":"2006.12497","title":"Technology Readiness Levels for AI & ML","created":"2020-06-21","cited_by_count":30},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27},{"id":"2106.13361","title":"Multifidelity Modeling for Physics-Informed Neural Networks (PINNs)","created":"2021-06-25","cited_by_count":25},{"id":"2404.14068","title":"Holistic Safety and Responsibility Evaluations of Advanced AI Models","created":"2024-04-22","cited_by_count":19},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14},{"id":"1705.02735","title":"Combating Human Trafficking with Deep Multimodal Models","created":"2017-05-08","cited_by_count":9},{"id":"2101.04454","title":"Learning Intuitive Physics with Multimodal Generative Models","created":"2021-01-12","cited_by_count":4},{"id":"2311.12670","title":"Towards a more inductive world for drug repurposing approaches","created":"2023-11-21","cited_by_count":4}],"next_cursor":null}