{"list":"other","total":55,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"2210.07128","title":"Language Models of Code are Few-Shot Commonsense Learners","created":"2022-10-13","cited_by_count":160},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104},{"id":"2210.03809","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","created":"2022-10-07","cited_by_count":94},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"2206.01201","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering","created":"2022-06-02","cited_by_count":59},{"id":"1905.04405","title":"Language-Conditioned Graph Networks for Relational Reasoning","created":"2019-05-10","cited_by_count":55},{"id":"2211.12914","title":"Open-vocabulary Attribute Detection","created":"2022-11-23","cited_by_count":29},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24},{"id":"2005.00724","title":"Obtaining Faithful Interpretations from Compositional Neural Networks","created":"2020-05-02","cited_by_count":23},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19},{"id":"1809.01810","title":"Interpretable Visual Question Answering by Reasoning on Dependency Trees","created":"2018-09-06","cited_by_count":15},{"id":"1806.02453","title":"Visual Reasoning by Progressive Module Networks","created":"2018-06-06","cited_by_count":7},{"id":"2210.08554","title":"COFAR: Commonsense and Factual Reasoning in Image Search","created":"2022-10-16","cited_by_count":4}],"next_cursor":null}