{"total":83,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2409.12959","title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","created":"2024-09-19","cited_by_count":101,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2412.18150","title":"EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation","created":"2024-12-24","cited_by_count":39,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2503.14908","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation","created":"2025-03-19","cited_by_count":36,"area":null},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2411.16781","title":"UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing","created":"2024-11-25","cited_by_count":18,"area":null},{"id":"2502.03183","title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2501.19098","title":"$\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation","created":"2025-01-31","cited_by_count":14,"area":null},{"id":"2503.09197","title":"Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2411.05001","title":"Analyzing The Language of Visual Tokens","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2510.08508","title":"MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration","created":"2025-10-09","cited_by_count":12,"area":null},{"id":"2505.19535","title":"TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2410.02505","title":"Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2504.16030","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","created":"2025-04-22","cited_by_count":9,"area":null},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2505.17476","title":"The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2505.23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2508.12291","title":"RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts","created":"2025-08-17","cited_by_count":8,"area":null},{"id":"2510.10231","title":"Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images","created":"2025-10-11","cited_by_count":8,"area":null},{"id":"2504.17828","title":"VEU-Bench: Towards Comprehensive Understanding of Video Editing","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2503.08173","title":"Towards All-in-One Medical Image Re-Identification","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2503.09949","title":"UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2506.14642","title":"3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2503.16423","title":"GAEA: A Geolocation Aware Conversational Assistant","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2505.17083","title":"Scale-invariant Attention","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2506.00893","title":"Affordance Benchmark for MLLMs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2511.14259","title":"ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation","created":"2025-11-18","cited_by_count":5,"area":null},{"id":"2512.04532","title":"PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2503.11170","title":"DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2509.19245","title":"ConViS-Bench: Estimating Video Similarity Through Semantic Concepts","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2509.25991","title":"Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2510.07310","title":"MATRIX: Mask Track Alignment for Interaction-aware Video Generation","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2512.10652","title":"TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2602.01173","title":"EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2509.23841","title":"Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2602.21956","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2411.16824","title":"Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge","created":"2024-11-25","cited_by_count":2,"area":null},{"id":"2511.06475","title":"NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2607.00983","title":"QCA: Query- and Content-Aware Keyframe Selection for Long Video Understanding","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2608.07014","title":"Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs","created":"2026-08-07","cited_by_count":2,"area":null},{"id":"2410.09729","title":"MIRAGE: Multimodal Identification and Recognition of Annotations in Indian General Prescriptions","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2504.10443","title":"Multimodal Long Video Modeling Based on Temporal Dynamic Context","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2506.02845","title":"Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2601.10369","title":"Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2603.29962","title":"SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2504.05463","title":"REVEAL: Relation-based Video Representation Learning for Video-Question-Answering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.24346","title":"VUDG: A Dataset for Video Understanding Domain Generalization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2512.05098","title":"Beyond Pixels: Benchmarking and Reward-Based Assessing Framework for Visual Spatial Aesthetics","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.10010","title":"VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.26683","title":"LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.27259","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2603.28363","title":"SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.11004","title":"Panoptic Pairwise Distortion Graph","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.06249","title":"GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.16601","title":"DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02096","title":"LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.26595","title":"SpatialQ: Understanding 3D Gaussian Splatting Scene Quality via Visual-based MLLM","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.03279","title":"3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.20713","title":"AGIDefect-4K: A Richly Annotated Dataset for AI-Generated Image Defect Detection, Localization and Explanation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.17112","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19664","title":"VideoResearcher: Self-Improving Tool Design for Long-Video Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.26205","title":"LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}