{"list":"closest","total":55,"rows":[{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67},{"id":"2407.08303","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","created":"2024-07-11","cited_by_count":73},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245},{"id":"2407.01509","title":"MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs","created":"2024-07-01","cited_by_count":62},{"id":"2406.17126","title":"MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs","created":"2024-06-24","cited_by_count":33},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2406.11840","title":"LLaNA: Large Language and NeRF Assistant","created":"2024-06-17","cited_by_count":6},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15},{"id":"2406.11230","title":"Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models","created":"2024-06-17","cited_by_count":55},{"id":"2406.10638","title":"Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly","created":"2024-06-15","cited_by_count":30},{"id":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2406.07230","title":"Needle In A Multimodal Haystack","created":"2024-06-11","cited_by_count":58},{"id":"2406.05862","title":"II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models","created":"2024-06-09","cited_by_count":16},{"id":"2406.03496","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","created":"2024-06-05","cited_by_count":23},{"id":"2406.02539","title":"Parrot: Multilingual Visual Instruction Tuning","created":"2024-06-04","cited_by_count":30},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2404.18532","title":"MileBench: Benchmarking MLLMs in Long Context","created":"2024-04-29","cited_by_count":88},{"id":"2404.16790","title":"SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension","created":"2024-04-25","cited_by_count":146},{"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":"2404.15592","title":"ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction","created":"2024-04-24","cited_by_count":17},{"id":"2404.12966","title":"Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning","created":"2024-04-19","cited_by_count":17},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2404.07922","title":"LaVy: Vietnamese Multimodal Large Language Model","created":"2024-04-11","cited_by_count":5},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101},{"id":"2403.01031","title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","created":"2024-03-01","cited_by_count":32},{"id":"2402.14973","title":"GenCeption: Evaluate Vision LLMs with Unlabeled Unimodal Data","created":"2024-02-22","cited_by_count":1},{"id":"2402.14154","title":"MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms","created":"2024-02-21","cited_by_count":26},{"id":"2402.13607","title":"CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models","created":"2024-02-21","cited_by_count":11},{"id":"2402.13220","title":"How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts","created":"2024-02-20","cited_by_count":47},{"id":"2402.12750","title":"Model Composition for Multimodal Large Language Models","created":"2024-02-20","cited_by_count":12},{"id":"2402.03173","title":"MULTI: Multimodal Understanding Leaderboard with Text and Images","created":"2024-02-05","cited_by_count":7},{"id":"2401.14011","title":"CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning","created":"2024-01-25","cited_by_count":31},{"id":"2401.11944","title":"CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark","created":"2024-01-22","cited_by_count":56},{"id":"2401.11943","title":"Benchmarking Large Multimodal Models against Common Corruptions","created":"2024-01-22","cited_by_count":24},{"id":"2401.10529","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","created":"2024-01-19","cited_by_count":94},{"id":"2401.07529","title":"MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception","created":"2024-01-15","cited_by_count":21},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2401.04471","title":"TransportationGames: Benchmarking Transportation Knowledge of (Multimodal) Large Language Models","created":"2024-01-09","cited_by_count":8},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41},{"id":"2311.17092","title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models","created":"2023-11-28","cited_by_count":97},{"id":"2311.02692","title":"ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models","created":"2023-11-05","cited_by_count":9},{"id":"2310.08475","title":"Can We Edit Multimodal Large Language Models?","created":"2023-10-12","cited_by_count":44},{"id":"2308.16890","title":"TouchStone: Evaluating Vision-Language Models by Language Models","created":"2023-08-31","cited_by_count":55},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102},{"id":"2308.04152","title":"Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions","created":"2023-08-08","cited_by_count":77},{"id":"2308.03729","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models","created":"2023-08-07","cited_by_count":9},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52}],"next_cursor":null}