{"total":36,"rows":[{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410,"area":"mllm"},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182,"area":"mllm"},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102,"area":"mllm"},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2406.07230","title":"Needle In A Multimodal Haystack","created":"2024-06-11","cited_by_count":58,"area":"mllm"},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34,"area":"mllm"},{"id":"2404.06332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","created":"2024-04-07","cited_by_count":22,"area":"mllm"},{"id":"2501.05031","title":"ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark","created":"2025-01-09","cited_by_count":19,"area":"mllm"},{"id":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"id":"2506.13589","title":"AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding","created":"2025-06-16","cited_by_count":15,"area":"mllm"},{"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":"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":"2503.17736","title":"V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction","created":"2025-03-22","cited_by_count":11,"area":"mllm"},{"id":"2406.13763","title":"Through the Theory of Mind's Eye: Reading Minds with Multimodal Video Large Language Models","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2603.26586","title":"MA-Bench: Towards Fine-grained Micro-Action Understanding","created":"2026-03-27","cited_by_count":9,"area":"mllm"},{"id":"2504.15270","title":"An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes","created":"2025-04-21","cited_by_count":7,"area":"mllm"},{"id":"2604.11102","title":"OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video","created":"2026-04-13","cited_by_count":6,"area":"mllm"},{"id":"2309.15915","title":"Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts","created":"2023-09-27","cited_by_count":5,"area":"mllm"},{"id":"2506.07032","title":"A Culturally-diverse Multilingual Multimodal Video Benchmark & Model","created":"2025-06-08","cited_by_count":5,"area":"mllm"},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2511.18399","title":"ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering","created":"2025-11-23","cited_by_count":4,"area":"mllm"},{"id":"2312.12716","title":"BloomVQA: Assessing Hierarchical Multi-modal Comprehension","created":"2023-12-20","cited_by_count":3,"area":"mllm"},{"id":"2501.07109","title":"The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering","created":"2025-01-13","cited_by_count":3,"area":"mllm"},{"id":"2508.03009","title":"Enhancing Long Video Question Answering with Scene-Localized Frame Grouping","created":"2025-08-05","cited_by_count":3,"area":"mllm"},{"id":"2603.24329","title":"GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents","created":"2026-03-25","cited_by_count":3,"area":"mllm"},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2607.02959","title":"Incentivizing Vision Language Models to Search for Long Video Question Answering","created":"2026-07-03","cited_by_count":2,"area":"mllm"},{"id":"2510.01009","title":"POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency","created":"2025-10-01","cited_by_count":1,"area":"mllm"},{"id":"2603.06828","title":"Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models","created":"2026-03-06","cited_by_count":1,"area":"mllm"},{"id":"2608.21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2506.04983","title":"TextVidBench: A Benchmark for Long Video Scene Text Understanding","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2603.24484","title":"Video-Only ToM: Enhancing Theory of Mind in Multimodal Large Language Models","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2606.19706","title":"NEST: Narrative Event Structures in Time for Long Video Understanding","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2609.39588","title":"KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":null}