{"list":"other","total":92,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"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":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1607.02533","title":"Adversarial examples in the physical world","created":"2016-07-08","cited_by_count":1769},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"1705.07204","title":"Ensemble Adversarial Training: Attacks and Defenses","created":"2017-05-19","cited_by_count":840},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"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":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"1805.06605","title":"Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models","created":"2018-05-17","cited_by_count":362},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290},{"id":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273},{"id":"1705.09064","title":"MagNet: a Two-Pronged Defense against Adversarial Examples","created":"2017-05-25","cited_by_count":269},{"id":"1702.04267","title":"On Detecting Adversarial Perturbations","created":"2017-02-14","cited_by_count":232},{"id":"2402.14289","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","created":"2024-02-22","cited_by_count":164},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103},{"id":"2203.06616","title":"LAS-AT: Adversarial Training with Learnable Attack Strategy","created":"2022-03-13","cited_by_count":95},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93},{"id":"2406.11839","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","created":"2024-06-17","cited_by_count":92},{"id":"2407.16216","title":"Reinforcement Learning for LLM Post-Training: A Survey","created":"2024-07-23","cited_by_count":92},{"id":"1902.04818","title":"The Odds are Odd: A Statistical Test for Detecting Adversarial Examples","created":"2019-02-13","cited_by_count":75},{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75},{"id":"1802.06816","title":"Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression","created":"2018-02-19","cited_by_count":74},{"id":"2405.15973","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","created":"2024-05-24","cited_by_count":74},{"id":"2408.10433","title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs","created":"2024-08-19","cited_by_count":49},{"id":"2303.15754","title":"Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization","created":"2023-03-28","cited_by_count":42},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37},{"id":"2304.00202","title":"Improving Fast Adversarial Training with Prior-Guided Knowledge","created":"2023-04-01","cited_by_count":35},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34},{"id":"2401.04727","title":"Revisiting Adversarial Training at Scale","created":"2024-01-09","cited_by_count":33},{"id":"2211.00525","title":"The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training","created":"2022-11-01","cited_by_count":23},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18},{"id":"2410.08503","title":"Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data","created":"2024-10-11","cited_by_count":12},{"id":"2410.12307","title":"DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain","created":"2024-10-16","cited_by_count":12},{"id":"2203.01439","title":"Enhancing Adversarial Robustness for Deep Metric Learning","created":"2022-03-02","cited_by_count":10},{"id":"2411.04376","title":"Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imaging","created":"2024-11-07","cited_by_count":10},{"id":"2405.11788","title":"TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models","created":"2024-05-20","cited_by_count":7},{"id":"2410.01574","title":"Adversarial Robustness of AI-Generated Image Detectors in the Real World","created":"2024-10-02","cited_by_count":7},{"id":"2410.12677","title":"Efficient Optimization Algorithms for Linear Adversarial Training","created":"2024-10-16","cited_by_count":6},{"id":"2411.08460","title":"Trap-MID: Trapdoor-based Defense against Model Inversion Attacks","created":"2024-11-13","cited_by_count":5},{"id":"2410.01617","title":"On Using Certified Training towards Empirical Robustness","created":"2024-10-02","cited_by_count":3},{"id":"2409.17589","title":"Improving Fast Adversarial Training via Self-Knowledge Guidance","created":"2024-09-26","cited_by_count":2},{"id":"2410.05951","title":"Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models","created":"2024-10-08","cited_by_count":2},{"id":"2410.17442","title":"Detecting Adversarial Examples","created":"2024-10-22","cited_by_count":2},{"id":"2410.21952","title":"On the Robustness of Adversarial Training Against Uncertainty Attacks","created":"2024-10-29","cited_by_count":2},{"id":"2411.00839","title":"CausAdv: A Causal-based Framework for Detecting Adversarial Examples","created":"2024-10-29","cited_by_count":2},{"id":"2411.02871","title":"Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training","created":"2024-11-05","cited_by_count":2}],"next_cursor":null}