{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"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":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513},{"id":"1907.05012","title":"Making AI Forget You: Data Deletion in Machine Learning","created":"2019-07-11","cited_by_count":465},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317},{"id":"2303.17591","title":"Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models","created":"2023-03-30","cited_by_count":301},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"2210.04610","title":"Red-Teaming the Stable Diffusion Safety Filter","created":"2022-10-03","cited_by_count":264},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1904.02239","title":"Hyperbolic Image Embeddings","created":"2019-04-03","cited_by_count":221},{"id":"1804.03329","title":"Representation Tradeoffs for Hyperbolic Embeddings","created":"2018-04-10","cited_by_count":206},{"id":"2005.00545","title":"Low-Dimensional Hyperbolic Knowledge Graph Embeddings","created":"2020-05-01","cited_by_count":195},{"id":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"1810.06546","title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","created":"2018-10-15","cited_by_count":156},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"1511.06361","title":"Order-Embeddings of Images and Language","created":"2015-11-19","cited_by_count":113},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"1806.04313","title":"Embedding Text in Hyperbolic Spaces","created":"2018-06-12","cited_by_count":76},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74},{"id":"2305.06611","title":"Hyperbolic Deep Learning in Computer Vision: A Survey","created":"2023-05-11","cited_by_count":73},{"id":"2212.00653","title":"Hyperbolic Contrastive Learning for Visual Representations beyond Objects","created":"2022-12-01","cited_by_count":61},{"id":"1705.10359","title":"Neural Embeddings of Graphs in Hyperbolic Space","created":"2017-05-29","cited_by_count":58},{"id":"2206.07835","title":"Disentangling visual and written concepts in CLIP","created":"2022-06-15","cited_by_count":58},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51},{"id":"1902.00913","title":"Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings","created":"2019-02-03","cited_by_count":49},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43},{"id":"2010.16143","title":"HyperText: Endowing FastText with Hyperbolic Geometry","created":"2020-10-30","cited_by_count":28},{"id":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27},{"id":"2303.14027","title":"Poincar\\'e ResNet","created":"2023-03-24","cited_by_count":25},{"id":"2211.06753","title":"Seamful XAI: Operationalizing Seamful Design in Explainable AI","created":"2022-11-12","cited_by_count":20},{"id":"2305.18962","title":"Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning","created":"2023-05-30","cited_by_count":18},{"id":"2305.18398","title":"Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?","created":"2023-05-28","cited_by_count":16},{"id":"2008.06716","title":"Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks","created":"2020-08-15","cited_by_count":13},{"id":"2108.04607","title":"Fully Hyperbolic Graph Convolution Network for Recommendation","created":"2021-08-10","cited_by_count":13},{"id":"2409.13079","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","created":"2024-09-19","cited_by_count":6},{"id":"2310.18918","title":"Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach","created":"2023-10-29","cited_by_count":5},{"id":"2304.02049","title":"Multi-Class Unlearning for Image Classification via Weight Filtering","created":"2023-04-04","cited_by_count":4}],"next_cursor":null}