{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1711.04574","title":"Learning Explanatory Rules from Noisy Data","created":"2017-11-13","cited_by_count":211},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1705.11040","title":"End-to-End Differentiable Proving","created":"2017-05-31","cited_by_count":161},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"2008.07912","title":"Inductive logic programming at 30: a new introduction","created":"2020-08-18","cited_by_count":85},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63},{"id":"2007.06477","title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","created":"2020-07-13","cited_by_count":60},{"id":"2307.07696","title":"Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text","created":"2023-07-15","cited_by_count":59},{"id":"2209.09554","title":"Towards Robust Referring Image Segmentation","created":"2022-09-20","cited_by_count":49},{"id":"2311.00571","title":"LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing","created":"2023-11-01","cited_by_count":47},{"id":"2312.08366","title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises","created":"2023-12-13","cited_by_count":41},{"id":"2006.11524","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","created":"2020-06-20","cited_by_count":35},{"id":"2307.07699","title":"Leveraging Large Language Models to Generate Answer Set Programs","created":"2023-07-15","cited_by_count":33},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33},{"id":"2102.11529","title":"Differentiable Logic Machines","created":"2021-02-23","cited_by_count":18},{"id":"2308.09472","title":"Vision Relation Transformer for Unbiased Scene Graph Generation","created":"2023-08-18","cited_by_count":18},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17},{"id":"2110.09383","title":"Neuro-Symbolic Forward Reasoning","created":"2021-10-18","cited_by_count":16},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13},{"id":"2307.00928","title":"Learning Differentiable Logic Programs for Abstract Visual Reasoning","created":"2023-07-03","cited_by_count":12},{"id":"2306.07743","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","created":"2023-06-13","cited_by_count":8},{"id":"2211.11650","title":"Neural Meta-Symbolic Reasoning and Learning","created":"2022-11-21","cited_by_count":4},{"id":"2208.13518","title":"LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems","created":"2022-08-29","cited_by_count":2}],"next_cursor":null}