{"total":58,"rows":[{"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,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67,"area":null},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52,"area":null},{"id":"2501.12612","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation","created":"2025-01-22","cited_by_count":48,"area":null},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2312.10763","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","created":"2023-12-17","cited_by_count":32,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28,"area":null},{"id":"2409.00031","title":"Quality Assessment in the Era of Large Models: A Survey","created":"2024-08-17","cited_by_count":26,"area":null},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25,"area":null},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21,"area":null},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2406.05343","title":"M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark","created":"2024-06-08","cited_by_count":14,"area":null},{"id":"2412.02158","title":"Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases","created":"2024-12-03","cited_by_count":14,"area":null},{"id":"2501.01243","title":"Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2410.10636","title":"Adapt-$\\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2508.11058","title":"Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset","created":"2025-08-14","cited_by_count":8,"area":null},{"id":"2501.19184","title":"A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2412.12661","title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","created":"2024-12-17","cited_by_count":6,"area":null},{"id":"2311.16673","title":"Large Language Models Meet Computer Vision: A Brief Survey","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2408.03516","title":"Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian","created":"2024-08-07","cited_by_count":5,"area":null},{"id":"2411.12293","title":"Generative Timelines for Instructed Visual Assembly","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2506.10395","title":"Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2505.16774","title":"IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2507.14555","title":"Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2507.14904","title":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2409.14484","title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization","created":"2024-09-22","cited_by_count":1,"area":null},{"id":"2507.12916","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2605.07367","title":"Weather-Robust Scene Semantics with Vision-Aligned 4D Radar","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.24553","title":"IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2310.06594","title":"On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2404.11064","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2409.07482","title":"VSLLaVA: a pipeline of large multimodal foundation model for industrial vibration signal analysis","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2506.01275","title":"Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2510.24434","title":"LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.14567","title":"SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2605.01359","title":"Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.04349","title":"MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.31148","title":"PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.05137","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}