{"total":169,"rows":[{"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":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"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":"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":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107,"area":"lr"},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"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":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2409.01156","title":"TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval","created":"2024-09-02","cited_by_count":40,"area":"inference"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2503.19951","title":"Audio-centric Video Understanding Benchmark without Text Shortcut","created":"2025-03-25","cited_by_count":36,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"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":"2505.20862","title":"AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding","created":"2025-05-27","cited_by_count":30,"area":"mllm"},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26,"area":"mllm"},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24,"area":"lr"},{"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":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2505.02064","title":"RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video","created":"2025-05-04","cited_by_count":21,"area":"lr"},{"id":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"area":null},{"id":"2501.02135","title":"AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs","created":"2025-01-03","cited_by_count":19,"area":"mllm"},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17,"area":null},{"id":"2410.11619","title":"MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval","created":"2024-10-15","cited_by_count":17,"area":null},{"id":"2310.03291","title":"Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction","created":"2023-10-05","cited_by_count":15,"area":"mllm"},{"id":"2509.18056","title":"TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs","created":"2025-09-22","cited_by_count":15,"area":"mllm"},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2504.00939","title":"WikiVideo: Article Generation from Multiple Videos","created":"2025-04-01","cited_by_count":13,"area":"rag"},{"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":"2407.06491","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11,"area":null},{"id":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2502.13363","title":"Pretrained Image-Text Models are Secretly Video Captioners","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2407.12508","title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline","created":"2024-07-17","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":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2506.06144","title":"CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval","created":"2025-06-06","cited_by_count":9,"area":null},{"id":"2509.00723","title":"OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination","created":"2025-08-31","cited_by_count":9,"area":"alignment"},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2503.18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2503.20698","title":"MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion","created":"2025-03-26","cited_by_count":8,"area":"mllm"},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"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":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","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":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2601.13143","title":"FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference","created":"2026-01-19","cited_by_count":7,"area":"inference"},{"id":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2506.23138","title":"VisualPrompter: Semantic-Aware Prompt Optimization with Visual Feedback for Text-to-Image Synthesis","created":"2025-06-29","cited_by_count":6,"area":null},{"id":"2508.12149","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2510.26027","title":"Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders","created":"2025-10-29","cited_by_count":6,"area":"mllm"},{"id":"2512.09841","title":"ChronusOmni: Improving Time Awareness of Omni Large Language Models","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2512.10324","title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","created":"2025-12-11","cited_by_count":6,"area":"inference"},{"id":"2604.14129","title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","created":"2026-04-15","cited_by_count":6,"area":"mllm"},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"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},{"id":"2601.18525","title":"Closing the Modality Gap Aligns Group-Wise Semantics","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5,"area":null},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2410.12109","title":"OMCAT: Omni Context Aware Transformer","created":"2024-10-15","cited_by_count":4,"area":"mllm"},{"id":"2501.18314","title":"AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment","created":"2025-01-30","cited_by_count":4,"area":"mllm"},{"id":"2502.02885","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.08887","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","created":"2025-06-10","cited_by_count":4,"area":null}],"next_cursor":"100"}