{"total":97,"rows":[{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322,"area":"mllm"},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251,"area":"lr"},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217,"area":"mllm"},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"area":null},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115,"area":"mllm"},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89,"area":"mllm"},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84,"area":"mllm"},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2406.04334","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","created":"2024-06-06","cited_by_count":75,"area":"mllm"},{"id":"2503.21483","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","created":"2025-03-27","cited_by_count":75,"area":"mllm"},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70,"area":"mllm"},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2410.16267","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs","created":"2024-10-21","cited_by_count":34,"area":"mllm"},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32,"area":"mllm"},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2409.20365","title":"VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs","created":"2024-09-30","cited_by_count":29,"area":"lr"},{"id":"2411.16819","title":"Pathways on the Image Manifold: Image Editing via Video Generation","created":"2024-11-25","cited_by_count":27,"area":"diffusion"},{"id":"2502.06428","title":"CoS: Chain-of-Shot Prompting for Long Video Understanding","created":"2025-02-10","cited_by_count":27,"area":"mllm"},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2509.24200","title":"UniVid: The Open-Source Unified Video Model","created":"2025-09-29","cited_by_count":19,"area":null},{"id":"2410.10441","title":"Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2504.20091","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","created":"2025-04-25","cited_by_count":16,"area":"lr"},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2503.16032","title":"Agentic Keyframe Search for Video Question Answering","created":"2025-03-20","cited_by_count":13,"area":"agents"},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2409.12963","title":"Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner","created":"2024-09-19","cited_by_count":11,"area":null},{"id":"2512.04000","title":"Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding","created":"2025-12-03","cited_by_count":11,"area":"mllm"},{"id":"2603.07135","title":"The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating","created":"2026-03-07","cited_by_count":11,"area":"mllm"},{"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":"2505.24158","title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders","created":"2025-05-30","cited_by_count":10,"area":"mllm"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"},{"id":"2411.17041","title":"Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM","created":"2024-11-26","cited_by_count":9,"area":"diffusion"},{"id":"2501.07214","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","created":"2025-01-13","cited_by_count":9,"area":null},{"id":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2511.18734","title":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2603.04977","title":"Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding","created":"2026-03-05","cited_by_count":8,"area":"lr"},{"id":"2505.03173","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2409.03206","title":"TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations","created":"2024-09-05","cited_by_count":6,"area":"lr"},{"id":"2503.04058","title":"EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2503.20472","title":"From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment","created":"2025-03-26","cited_by_count":6,"area":"mllm"},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2602.03615","title":"KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs","created":"2026-02-03","cited_by_count":6,"area":"mllm"},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2504.17213","title":"MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding","created":"2025-04-24","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":"2411.15453","title":"Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy","created":"2024-11-23","cited_by_count":4,"area":"mllm"},{"id":"2504.09583","title":"AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding","created":"2025-04-13","cited_by_count":4,"area":"agents"},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2509.14199","title":"Dense Video Understanding with Gated Residual Tokenization","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2512.09354","title":"Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding","created":"2025-12-10","cited_by_count":4,"area":"lr"},{"id":"2507.15569","title":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","created":"2025-07-21","cited_by_count":3,"area":"mllm"},{"id":"2503.11205","title":"LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2510.06973","title":"Addressing the ID-Matching Challenge in Long Video Captioning","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2510.08818","title":"D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition","created":"2025-10-09","cited_by_count":2,"area":"mllm"},{"id":"2601.06600","title":"Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation","created":"2026-01-10","cited_by_count":2,"area":"mllm"},{"id":"2604.02891","title":"Progressive Video Condensation with MLLM Agent for Long-form Video Understanding","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2607.01737","title":"ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2505.19125","title":"RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models","created":"2025-05-25","cited_by_count":1,"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":"2511.01617","title":"Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.09104","title":"Training-free Motion Factorization for Compositional Video Generation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.11220","title":"Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2603.17948","title":"VideoAtlas: Navigating Long-Form Video in Logarithmic Compute","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.01662","title":"Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models","created":"2026-05-03","cited_by_count":1,"area":"mllm"},{"id":"2411.05734","title":"Poze: Sports Technique Feedback under Data Constraints","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2411.19951","title":"Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation","created":"2024-11-29","cited_by_count":0,"area":"mllm"},{"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":"2505.24371","title":"Grid-LOGAT: Grid Based Local and Global Area Transcription for Video Question Answering","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2511.20201","title":"GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2604.12115","title":"HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models","created":"2026-04-13","cited_by_count":0,"area":"mllm"},{"id":"2605.02262","title":"WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization","created":"2026-05-04","cited_by_count":0,"area":"inference"},{"id":"2605.22078","title":"Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.27885","title":"Reflective Dialogue between Teacher and Solver Agents for Video Question Answering","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.29445","title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","created":"2026-06-28","cited_by_count":0,"area":"mllm"},{"id":"2608.07537","title":"An evolutionary model of animats with VLM-based subjective evaluation","created":"2026-07-29","cited_by_count":0,"area":"mllm"},{"id":"2608.14016","title":"Content Based Video Narration of Gameplay with Vision Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.15058","title":"MEDR: Query-Independent Frame Selection via Multi-Signal Event Modeling and Dynamic Rescoring","created":"2026-08-15","cited_by_count":0,"area":"mllm"},{"id":"2609.07941","title":"ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.26056","title":"CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching","created":"2026-08-08","cited_by_count":0,"area":"mllm"},{"id":"2610.00809","title":"Paying for Too Many Tokens? Valid and Cost-Efficient Multimodal LLM Annotation with Simple Heuristics","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":null}