{"list":"other","total":51,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"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":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"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":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"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":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"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":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"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":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2012.14660","title":"A Theoretical Analysis of the Repetition Problem in Text Generation","created":"2020-12-29","cited_by_count":83},{"id":"2401.11170","title":"Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images","created":"2024-01-20","cited_by_count":69},{"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":"1904.05181","title":"Black-box Adversarial Attacks on Video Recognition Models","created":"2019-04-10","cited_by_count":58},{"id":"2310.10226","title":"Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective","created":"2023-10-16","cited_by_count":39},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37},{"id":"2504.14218","title":"Understanding the Repeat Curse in Large Language Models from a Feature Perspective","created":"2025-04-19","cited_by_count":37},{"id":"2506.07180","title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","created":"2025-06-08","cited_by_count":21},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20},{"id":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19},{"id":"2504.20472","title":"Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction","created":"2025-04-29","cited_by_count":16},{"id":"2107.04284","title":"Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems","created":"2021-07-09","cited_by_count":14},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11},{"id":"2503.21824","title":"Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations","created":"2025-03-26","cited_by_count":5},{"id":"2508.10974","title":"Failures to Surface Harmful Contents in Video Large Language Models","created":"2025-08-14","cited_by_count":5},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4},{"id":"2408.12099","title":"Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing","created":"2024-08-22","cited_by_count":3}],"next_cursor":null}