{"total":154,"rows":[{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040,"area":null},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547,"area":"mllm"},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317,"area":null},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195,"area":"mllm"},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2409.10197","title":"Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models","created":"2024-09-16","cited_by_count":126,"area":"mllm"},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96,"area":"mllm"},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81,"area":"mllm"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68,"area":null},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68,"area":"mllm"},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2405.12523","title":"Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models","created":"2024-05-21","cited_by_count":46,"area":"mllm"},{"id":"2304.04227","title":"Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions","created":"2023-04-09","cited_by_count":42,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2306.04362","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","created":"2023-06-07","cited_by_count":36,"area":"mllm"},{"id":"2311.16511","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","created":"2023-11-25","cited_by_count":36,"area":"mllm"},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"area":null},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2402.02460","title":"Review of multimodal machine learning approaches in healthcare","created":"2024-02-04","cited_by_count":31,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2411.15411","title":"FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity","created":"2024-11-23","cited_by_count":27,"area":"mllm"},{"id":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26,"area":"mllm"},{"id":"2503.00936","title":"IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis","created":"2025-03-02","cited_by_count":26,"area":null},{"id":"2305.06002","title":"InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation","created":"2023-05-10","cited_by_count":25,"area":null},{"id":"2311.05348","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","created":"2023-11-09","cited_by_count":24,"area":"mllm"},{"id":"2403.07304","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","created":"2024-03-12","cited_by_count":24,"area":"mllm"},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","cited_by_count":19,"area":null},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2406.18113","title":"Chrono: A Simple Blueprint for Representing Time in MLLMs","created":"2024-06-26","cited_by_count":18,"area":"mllm"},{"id":"2506.01663","title":"Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement","created":"2025-06-02","cited_by_count":18,"area":"mllm"},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2407.15350","title":"WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16,"area":"mllm"},{"id":"2305.02177","title":"Transforming Visual Scene Graphs to Image Captions","created":"2023-05-03","cited_by_count":15,"area":"moe"},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2311.17095","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","created":"2023-11-28","cited_by_count":15,"area":"mllm"},{"id":"2311.14199","title":"A Systematic Review of Deep Learning-based Research on Radiology Report Generation","created":"2023-11-23","cited_by_count":14,"area":null},{"id":"2401.10711","title":"Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering","created":"2024-01-19","cited_by_count":14,"area":"mllm"},{"id":"2402.16050","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","created":"2024-02-25","cited_by_count":14,"area":"mllm"},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2310.04991","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2504.07836","title":"AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2308.05822","title":"Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception","created":"2023-08-10","cited_by_count":9,"area":null},{"id":"2410.20034","title":"Sensor2Text: Enabling Natural Language Interactions for Daily Activity Tracking Using Wearable Sensors","created":"2024-10-26","cited_by_count":9,"area":null},{"id":"2503.20502","title":"MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning","created":"2025-03-26","cited_by_count":9,"area":"mllm"},{"id":"2311.12327","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","created":"2023-11-21","cited_by_count":8,"area":"mllm"},{"id":"2312.00347","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2307.03153","title":"MultiVENT: Multilingual Videos of Events with Aligned Natural Text","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2312.06363","title":"MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2504.20185","title":"AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services","created":"2025-04-28","cited_by_count":7,"area":null},{"id":"2511.21331","title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","created":"2025-11-26","cited_by_count":7,"area":null},{"id":"2411.09439","title":"Spider: Any-to-Many Multimodal LLM","created":"2024-11-14","cited_by_count":6,"area":"mllm"},{"id":"2509.02969","title":"VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2606.23327","title":"VideoAgent: All-in-One Framework for Video Understanding and Editing","created":"2026-06-22","cited_by_count":6,"area":null},{"id":"2307.08504","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","created":"2023-07-17","cited_by_count":5,"area":"mllm"},{"id":"2401.17797","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2405.00954","title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null}],"next_cursor":"100"}