{"total":140,"rows":[{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729,"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":"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":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"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":"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2409.15272","title":"OmniBench: Towards The Future of Universal Omni-Language Models","created":"2024-09-23","cited_by_count":102,"area":"mllm"},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"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":"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":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68,"area":"mllm"},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"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":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63,"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":"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":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"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":"2505.18657","title":"MLLMs are Deeply Affected by Modality Bias","created":"2025-05-24","cited_by_count":40,"area":"mllm"},{"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":"2404.14381","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29,"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":"2411.01053","title":"Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities","created":"2024-11-01","cited_by_count":24,"area":null},{"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":"2305.08381","title":"Parameter-efficient Tuning of Large-scale Multimodal Foundation Model","created":"2023-05-15","cited_by_count":23,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2403.16276","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","created":"2024-03-24","cited_by_count":18,"area":"mllm"},{"id":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18,"area":"lr"},{"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":"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":"2403.00691","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2506.05328","title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs","created":"2025-06-05","cited_by_count":16,"area":"lr"},{"id":"2401.09774","title":"On the Audio Hallucinations in Large Audio-Video Language Models","created":"2024-01-18","cited_by_count":15,"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":"2407.20693","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","created":"2024-07-30","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":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2412.10749","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","created":"2024-12-14","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"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":"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":"2503.04459","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"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":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2508.12687","title":"EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding","created":"2025-08-18","cited_by_count":10,"area":"mllm"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"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":"2311.01620","title":"ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8,"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":"2311.06218","title":"Semantic-aware Video Representation for Few-shot Action Recognition","created":"2023-11-10","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":"2505.18110","title":"Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"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":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","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":"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":"2603.03192","title":"MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization","created":"2026-03-03","cited_by_count":6,"area":"alignment"},{"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":"2307.03254","title":"Vision Language Transformers: A Survey","created":"2023-07-06","cited_by_count":5,"area":"mllm"},{"id":"2406.09412","title":"Explore the Limits of Omni-modal Pretraining at Scale","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","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":"2309.08612","title":"Explaining Vision and Language through Graphs of Events in Space and Time","created":"2023-08-29","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":"2503.11392","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","created":"2025-03-14","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":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.07576","title":"Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding","created":"2025-06-09","cited_by_count":4,"area":"wm"},{"id":"2506.21813","title":"CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2507.14935","title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2509.26278","title":"ProfVLM: A lightweight video-language model for multi-view proficiency estimation","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2305.11769","title":"Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner","created":"2023-05-19","cited_by_count":3,"area":"mllm"},{"id":"2309.03884","title":"Zero-Shot Audio Captioning via Audibility Guidance","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2409.00851","title":"Dissecting Temporal Understanding in Text-to-Audio Retrieval","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2411.02851","title":"Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2412.20872","title":"LINK: Adaptive Modality Interaction for Audio-Visual Video Parsing","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2503.20633","title":"Enhancing Multi-modal Models with Heterogeneous MoE Adapters for Fine-tuning","created":"2025-03-26","cited_by_count":3,"area":"moe"},{"id":"2505.07841","title":"Task-Oriented Multimodal Token Transmission in Resource-Constrained Multiuser Networks","created":"2025-05-06","cited_by_count":3,"area":null},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.12034","title":"Calibrated Multimodal Representation Learning with Missing Modalities","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2512.16925","title":"V-Agent: An Interactive Video Search System Using Vision-Language Models","created":"2025-11-04","cited_by_count":3,"area":"mllm"},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null}],"next_cursor":"100"}