{"list":"other","total":168,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"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":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"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":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207},{"id":"1711.03902","title":"Neural-Symbolic Learning and Reasoning: A Survey and Interpretation","created":"2017-11-10","cited_by_count":196},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129},{"id":"2302.14042","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","created":"2023-02-27","cited_by_count":128},{"id":"2112.08614","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","created":"2021-12-16","cited_by_count":126},{"id":"2012.11014","title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","created":"2020-12-20","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":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113},{"id":"1902.02960","title":"Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making","created":"2019-02-08","cited_by_count":109},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"2402.07945","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","created":"2024-02-09","cited_by_count":102},{"id":"2210.03809","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","created":"2022-10-07","cited_by_count":94},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92},{"id":"2505.19255","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","created":"2025-05-25","cited_by_count":90},{"id":"1511.02570","title":"Explicit Knowledge-based Reasoning for Visual Question Answering","created":"2015-11-09","cited_by_count":85},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85},{"id":"2304.11116","title":"Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT","created":"2023-04-10","cited_by_count":80},{"id":"2010.06002","title":"Thinking Fast and Slow in AI","created":"2020-10-12","cited_by_count":70},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68},{"id":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63},{"id":"2407.12735","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","created":"2024-07-17","cited_by_count":62},{"id":"2401.12863","title":"KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning","created":"2024-01-23","cited_by_count":60},{"id":"2206.01201","title":"REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering","created":"2022-06-02","cited_by_count":59},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2303.13483","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","created":"2023-03-23","cited_by_count":57},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56},{"id":"2006.09073","title":"Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering","created":"2020-06-16","cited_by_count":51},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50},{"id":"2406.07089","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","created":"2024-06-11","cited_by_count":49},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48},{"id":"1603.02814","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","created":"2016-03-09","cited_by_count":44},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44},{"id":"2307.11986","title":"Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering","created":"2023-07-22","cited_by_count":41},{"id":"1902.07864","title":"Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering","created":"2019-02-21","cited_by_count":38},{"id":"2107.05348","title":"Zero-shot Visual Question Answering using Knowledge Graph","created":"2021-07-12","cited_by_count":37},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36},{"id":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33},{"id":"2009.00145","title":"Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering","created":"2020-08-31","cited_by_count":32},{"id":"2303.00534","title":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","created":"2023-03-01","cited_by_count":31},{"id":"1809.01124","title":"Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering","created":"2018-09-04","cited_by_count":30},{"id":"2308.11186","title":"Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models","created":"2023-08-22","cited_by_count":30},{"id":"2311.00967","title":"Vision-Language Interpreter for Robot Task Planning","created":"2023-11-02","cited_by_count":30},{"id":"2109.07872","title":"Knowledge-based Embodied Question Answering","created":"2021-09-16","cited_by_count":29},{"id":"2408.00555","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","created":"2024-08-01","cited_by_count":29},{"id":"2402.11943","title":"LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation","created":"2024-02-19","cited_by_count":28},{"id":"1908.02962","title":"CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense","created":"2019-08-08","cited_by_count":27},{"id":"2305.03660","title":"Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models","created":"2023-05-05","cited_by_count":27},{"id":"2309.07726","title":"GRID: Scene-Graph-based Instruction-driven Robotic Task Planning","created":"2023-09-14","cited_by_count":27},{"id":"2405.09713","title":"SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge","created":"2024-05-15","cited_by_count":25},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24},{"id":"2403.13805","title":"RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition","created":"2024-03-20","cited_by_count":24},{"id":"2304.08587","title":"Grounding Classical Task Planners via Vision-Language Models","created":"2023-04-17","cited_by_count":23},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22},{"id":"2107.05080","title":"Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration","created":"2021-07-11","cited_by_count":21},{"id":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20},{"id":"2105.13073","title":"Maria: A Visual Experience Powered Conversational Agent","created":"2021-05-27","cited_by_count":19},{"id":"2306.16650","title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","created":"2023-06-29","cited_by_count":19},{"id":"2205.10178","title":"Visually-Augmented Language Modeling","created":"2022-05-20","cited_by_count":18},{"id":"2206.14989","title":"A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA","created":"2022-06-30","cited_by_count":18},{"id":"2207.12888","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","created":"2022-07-26","cited_by_count":18},{"id":"2406.00622","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","created":"2024-06-02","cited_by_count":18}],"next_cursor":"100"}