{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"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":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"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":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"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":"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":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"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":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"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":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144},{"id":"2307.14061","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","created":"2023-07-26","cited_by_count":108},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83},{"id":"2404.12387","title":"Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models","created":"2024-04-18","cited_by_count":67},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37},{"id":"2105.03592","title":"De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks","created":"2021-05-08","cited_by_count":33},{"id":"2404.16452","title":"PAD: Patch-Agnostic Defense against Adversarial Patch Attacks","created":"2024-04-25","cited_by_count":32},{"id":"2504.17447","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","created":"2025-04-24","cited_by_count":27},{"id":"2503.03613","title":"CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP","created":"2025-03-05","cited_by_count":23},{"id":"2103.02927","title":"QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval","created":"2021-03-04","cited_by_count":22},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21},{"id":"2002.11293","title":"Adversarial Ranking Attack and Defense","created":"2020-02-26","cited_by_count":14},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13},{"id":"2501.08415","title":"Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics","created":"2025-01-14","cited_by_count":9},{"id":"2501.01042","title":"Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach","created":"2025-01-02","cited_by_count":7},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","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}],"next_cursor":null}