{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"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":543},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2312.14135","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","created":"2023-12-21","cited_by_count":482},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178},{"id":"1807.04225","title":"Measuring abstract reasoning in neural networks","created":"2018-07-11","cited_by_count":166},{"id":"2212.05206","title":"Thinking Fast and Slow in Large Language Models","created":"2022-12-10","cited_by_count":137},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"2305.18354","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","created":"2023-05-26","cited_by_count":82},{"id":"2107.00637","title":"Generalization and Robustness Implications in Object-Centric Learning","created":"2021-07-01","cited_by_count":81},{"id":"2002.06838","title":"Stratified Rule-Aware Network for Abstract Visual Reasoning","created":"2020-02-17","cited_by_count":72},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72},{"id":"1603.01312","title":"Learning Physical Intuition of Block Towers by Example","created":"2016-03-03","cited_by_count":68},{"id":"2405.13872","title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models","created":"2024-05-22","cited_by_count":65},{"id":"2401.02582","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","created":"2024-01-05","cited_by_count":56},{"id":"2012.14601","title":"Emergent Symbols through Binding in External Memory","created":"2020-12-29","cited_by_count":47},{"id":"2009.09405","title":"Scale-Localized Abstract Reasoning","created":"2020-09-20","cited_by_count":45},{"id":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37},{"id":"2202.10284","title":"A Review of Emerging Research Directions in Abstract Visual Reasoning","created":"2022-02-21","cited_by_count":33},{"id":"2404.13591","title":"MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning","created":"2024-04-21","cited_by_count":30},{"id":"2403.04732","title":"How Far Are We from Intelligent Visual Deductive Reasoning?","created":"2024-03-07","cited_by_count":29},{"id":"2311.09048","title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models","created":"2023-11-15","cited_by_count":28},{"id":"2309.06629","title":"The Relational Bottleneck as an Inductive Bias for Efficient Abstraction","created":"2023-09-12","cited_by_count":27},{"id":"2306.02500","title":"Systematic Visual Reasoning through Object-Centric Relational Abstraction","created":"2023-06-04","cited_by_count":20},{"id":"2303.04091","title":"Abstract Visual Reasoning Enabled by Language","created":"2023-03-07","cited_by_count":15},{"id":"2403.03458","title":"Slot Abstractors: Toward Scalable Abstract Visual Reasoning","created":"2024-03-06","cited_by_count":11},{"id":"2001.10857","title":"Evaluating the Progress of Deep Learning for Visual Relational Concepts","created":"2020-01-29","cited_by_count":9},{"id":"2303.11730","title":"Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices","created":"2023-03-21","cited_by_count":9},{"id":"2312.09997","title":"One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems","created":"2023-12-15","cited_by_count":6}],"next_cursor":null}