{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2207.05382","title":"Frequency Domain Model Augmentation for Adversarial Attack","created":"2022-07-12","cited_by_count":130},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103},{"id":"2312.03777","title":"On the Robustness of Large Multimodal Models Against Image Adversarial Attacks","created":"2023-12-06","cited_by_count":92},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84},{"id":"2210.00586","title":"Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2","created":"2022-10-02","cited_by_count":55},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45},{"id":"2310.03185","title":"Misusing Tools in Large Language Models With Visual Adversarial Examples","created":"2023-10-04","cited_by_count":42},{"id":"2405.19802","title":"Exploring the Robustness of Decision-Level Through Adversarial Attacks on LLM-Based Embodied Models","created":"2024-05-30","cited_by_count":33},{"id":"2407.09829","title":"VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation","created":"2024-07-13","cited_by_count":33},{"id":"2307.12280","title":"Downstream-agnostic Adversarial Examples","created":"2023-07-23","cited_by_count":32},{"id":"2409.17874","title":"DarkSAM: Fooling Segment Anything Model to Segment Nothing","created":"2024-09-26","cited_by_count":32},{"id":"2408.01428","title":"Transferable Adversarial Facial Images for Privacy Protection","created":"2024-07-18","cited_by_count":27},{"id":"2410.06699","title":"Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models","created":"2024-10-09","cited_by_count":27},{"id":"2405.09981","title":"Adversarial Robustness for Visual Grounding of Multimodal Large Language Models","created":"2024-05-16","cited_by_count":23},{"id":"2409.17143","title":"Attention Prompting on Image for Large Vision-Language Models","created":"2024-09-25","cited_by_count":23},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23},{"id":"2403.10801","title":"Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples","created":"2024-03-16","cited_by_count":21},{"id":"2412.16955","title":"NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors","created":"2024-12-22","cited_by_count":17},{"id":"2412.16651","title":"PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation","created":"2024-12-21","cited_by_count":14},{"id":"2503.15293","title":"Test-Time Backdoor Detection for Object Detection Models","created":"2025-03-19","cited_by_count":14},{"id":"2412.16958","title":"Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature","created":"2024-12-22","cited_by_count":13},{"id":"2304.10783","title":"Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning","created":"2023-04-21","cited_by_count":10},{"id":"2505.23828","title":"Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM","created":"2025-05-28","cited_by_count":10}],"next_cursor":null}