{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1610.08401","title":"Universal adversarial perturbations","created":"2016-10-26","cited_by_count":784},{"id":"1912.00049","title":"Square Attack: a query-efficient black-box adversarial attack via random search","created":"2019-11-29","cited_by_count":685},{"id":"1803.06978","title":"Improving Transferability of Adversarial Examples with Input Diversity","created":"2018-03-19","cited_by_count":599},{"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":"1611.02770","title":"Delving into Transferable Adversarial Examples and Black-box Attacks","created":"2016-11-08","cited_by_count":536},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"1904.02884","title":"Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks","created":"2019-04-05","cited_by_count":442},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273},{"id":"1901.01588","title":"PyOD: A Python Toolbox for Scalable Outlier Detection","created":"2019-01-06","cited_by_count":222},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144},{"id":"1906.06032","title":"Adversarial Training Can Hurt Generalization","created":"2019-06-14","cited_by_count":132},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"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":"2311.16101","title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","created":"2023-11-27","cited_by_count":108},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"2012.11207","title":"On Success and Simplicity: A Second Look at Transferable Targeted Attacks","created":"2020-12-21","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":"2306.12422","title":"DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation","created":"2023-06-21","cited_by_count":81},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75},{"id":"2005.13525","title":"Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models","created":"2020-05-27","cited_by_count":58},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2401.04350","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","created":"2024-01-09","cited_by_count":48},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48},{"id":"2410.05346","title":"AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models","created":"2024-10-07","cited_by_count":46},{"id":"2310.17626","title":"A Survey on Transferability of Adversarial Examples across Deep Neural Networks","created":"2023-10-26","cited_by_count":44},{"id":"2311.11261","title":"Adversarial Prompt Tuning for Vision-Language Models","created":"2023-11-19","cited_by_count":44},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44},{"id":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39},{"id":"2307.12280","title":"Downstream-agnostic Adversarial Examples","created":"2023-07-23","cited_by_count":32},{"id":"2308.11804","title":"Adversarial Illusions in Multi-Modal Embeddings","created":"2023-08-22","cited_by_count":29},{"id":"2404.19287","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","created":"2024-04-30","cited_by_count":28},{"id":"2410.15461","title":"EVA: An Embodied World Model for Future Video Anticipation","created":"2024-10-20","cited_by_count":28},{"id":"2410.21802","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models","created":"2024-10-29","cited_by_count":23},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22},{"id":"1704.02223","title":"An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges","created":"2017-04-07","cited_by_count":21},{"id":"2307.14682","title":"Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical World","created":"2023-07-27","cited_by_count":21},{"id":"2404.05264","title":"Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security","created":"2024-04-08","cited_by_count":19},{"id":"2308.12636","title":"Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learning","created":"2023-08-24","cited_by_count":16},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15},{"id":"2308.14597","title":"Adversarial Attacks on Foundational Vision Models","created":"2023-08-28","cited_by_count":13},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13},{"id":"2407.00020","title":"Visual Language Model based Cross-modal Semantic Communication Systems","created":"2024-05-06","cited_by_count":12},{"id":"2409.06793","title":"Adversarial Attacks to Multi-Modal Models","created":"2024-09-10","cited_by_count":12},{"id":"2312.04231","title":"Adventures of Trustworthy Vision-Language Models: A Survey","created":"2023-12-07","cited_by_count":10},{"id":"2403.10883","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","created":"2024-03-16","cited_by_count":7},{"id":"2011.09832","title":"Differentiable Data Augmentation with Kornia","created":"2020-11-19","cited_by_count":4}],"next_cursor":null}