{"list":"other","total":80,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"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},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2310.16045","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","created":"2023-10-24","cited_by_count":226},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"2312.03594","title":"A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting","created":"2023-12-06","cited_by_count":169},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145},{"id":"2312.03777","title":"On the Robustness of Large Multimodal Models Against Image Adversarial Attacks","created":"2023-12-06","cited_by_count":92},{"id":"2406.11839","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","created":"2024-06-17","cited_by_count":92},{"id":"2406.16338","title":"VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models","created":"2024-06-24","cited_by_count":90},{"id":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68},{"id":"2411.02712","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","created":"2024-11-05","cited_by_count":67},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62},{"id":"2411.06686","title":"SeedEdit: Align Image Re-Generation to Image Editing","created":"2024-11-11","cited_by_count":61},{"id":"2407.06192","title":"Multi-Object Hallucination in Vision-Language Models","created":"2024-07-08","cited_by_count":60},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57},{"id":"2402.03746","title":"Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback","created":"2024-02-06","cited_by_count":36},{"id":"2503.15138","title":"VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention","created":"2025-03-19","cited_by_count":36},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35},{"id":"2410.17637","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","created":"2024-10-23","cited_by_count":34},{"id":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34},{"id":"2504.13169","title":"Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling","created":"2025-04-17","cited_by_count":33},{"id":"2406.10900","title":"AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models","created":"2024-06-16","cited_by_count":32},{"id":"2501.16629","title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs","created":"2025-01-28","cited_by_count":31},{"id":"2406.16562","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","created":"2024-06-24","cited_by_count":20},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20},{"id":"2503.19622","title":"Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation","created":"2025-03-25","cited_by_count":20},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17},{"id":"2504.05810","title":"PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning","created":"2025-04-08","cited_by_count":17},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17},{"id":"2503.14378","title":"Impossible Videos","created":"2025-03-18","cited_by_count":16},{"id":"2409.00755","title":"Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification","created":"2024-09-01","cited_by_count":15},{"id":"2502.13928","title":"Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images","created":"2025-02-19","cited_by_count":14},{"id":"2401.10222","title":"Supervised Fine-tuning in turn Improves Visual Foundation Models","created":"2024-01-18","cited_by_count":13},{"id":"2404.09640","title":"CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning","created":"2024-04-15","cited_by_count":12},{"id":"2503.18406","title":"Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning","created":"2025-03-24","cited_by_count":9},{"id":"2507.10432","title":"Text-Visual Semantic Constrained AI-Generated Image Quality Assessment","created":"2025-07-14","cited_by_count":6},{"id":"2509.12718","title":"EvoEmpirBench: Dynamic Spatial Reasoning with Agent-ExpVer","created":"2025-09-16","cited_by_count":5},{"id":"2606.18847","title":"WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents","created":"2026-06-17","cited_by_count":5},{"id":"2512.00953","title":"Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval","created":"2025-11-30","cited_by_count":4},{"id":"2604.00558","title":"STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO","created":"2026-04-01","cited_by_count":4},{"id":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4},{"id":"2604.16243","title":"Find, Fix, Reason: Context Repair for Video Reasoning","created":"2026-04-17","cited_by_count":3},{"id":"2606.00828","title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","created":"2026-05-30","cited_by_count":3},{"id":"2503.21541","title":"LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing","created":"2025-03-27","cited_by_count":2}],"next_cursor":null}