{"list":"other","total":61,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"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":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280},{"id":"2406.09403","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","created":"2024-06-13","cited_by_count":268},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206},{"id":"2404.16006","title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","created":"2024-04-24","cited_by_count":193},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173},{"id":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160},{"id":"2406.13642","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","created":"2024-06-19","cited_by_count":152},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101},{"id":"2408.03361","title":"GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI","created":"2024-08-06","cited_by_count":96},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76},{"id":"2409.00147","title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","created":"2024-08-30","cited_by_count":70},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66},{"id":"2410.06468","title":"Does Spatial Cognition Emerge in Frontier Models?","created":"2024-10-09","cited_by_count":66},{"id":"2010.00763","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","created":"2020-10-02","cited_by_count":63},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63},{"id":"2501.10074","title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","created":"2025-01-17","cited_by_count":62},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49},{"id":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34},{"id":"2311.00047","title":"Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?","created":"2023-10-31","cited_by_count":32},{"id":"2403.15952","title":"IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models","created":"2024-03-23","cited_by_count":31},{"id":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","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":"2406.12203","title":"InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context","created":"2024-06-18","cited_by_count":26},{"id":"2501.15558","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model","created":"2025-01-26","cited_by_count":25},{"id":"2311.09241","title":"Chain of Images for Intuitively Reasoning","created":"2023-11-09","cited_by_count":21},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21},{"id":"2409.13729","title":"MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model","created":"2024-09-10","cited_by_count":21},{"id":"2311.05591","title":"Multimodal Foundation Models Exploit Text to Make Medical Image Predictions","created":"2023-11-09","cited_by_count":20},{"id":"2401.13311","title":"ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models","created":"2024-01-24","cited_by_count":19},{"id":"2404.13957","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","created":"2024-04-22","cited_by_count":19},{"id":"2310.10207","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","created":"2023-10-16","cited_by_count":18},{"id":"2502.15969","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","created":"2025-02-21","cited_by_count":16},{"id":"2406.05343","title":"M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark","created":"2024-06-08","cited_by_count":14},{"id":"2304.11111","title":"Inducing anxiety in large language models can induce bias","created":"2023-04-21","cited_by_count":10},{"id":"2310.20499","title":"Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models","created":"2023-10-31","cited_by_count":8},{"id":"2402.17793","title":"A Surprising Failure? Multimodal LLMs and the NLVR Challenge","created":"2024-02-26","cited_by_count":4}],"next_cursor":null}