{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"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":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"1911.08411","title":"Mixed-curvature Variational Autoencoders","created":"2019-11-19","cited_by_count":86},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74},{"id":"2403.02781","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","created":"2024-03-05","cited_by_count":72},{"id":"2206.10044","title":"Identifiability of deep generative models without auxiliary information","created":"2022-06-20","cited_by_count":70},{"id":"2107.11472","title":"Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers","created":"2021-07-23","cited_by_count":57},{"id":"2505.23883","title":"BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning","created":"2025-05-29","cited_by_count":50},{"id":"2404.00851","title":"Prompt Learning via Meta-Regularization","created":"2024-04-01","cited_by_count":26},{"id":"2505.24722","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","created":"2025-05-30","cited_by_count":26},{"id":"2304.05059","title":"Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification","created":"2023-04-11","cited_by_count":23},{"id":"2310.01211","title":"From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication","created":"2023-10-02","cited_by_count":21},{"id":"2405.03188","title":"Hyperbolic Geometric Latent Diffusion Model for Graph Generation","created":"2024-05-06","cited_by_count":20},{"id":"2405.19547","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","created":"2024-05-29","cited_by_count":20},{"id":"2406.17720","title":"BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity","created":"2024-06-25","cited_by_count":20},{"id":"2306.11180","title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","created":"2023-06-19","cited_by_count":18},{"id":"2406.00519","title":"Learning Discrete Concepts in Latent Hierarchical Models","created":"2024-06-01","cited_by_count":17},{"id":"2412.14695","title":"Lorentzian Residual Neural Networks","created":"2024-12-19","cited_by_count":17},{"id":"2208.01188","title":"Curved Geometric Networks for Visual Anomaly Recognition","created":"2022-08-02","cited_by_count":15},{"id":"2304.03931","title":"Exploring Data Geometry for Continual Learning","created":"2023-04-08","cited_by_count":15},{"id":"2209.15217","title":"Hyperbolic VAE via Latent Gaussian Distributions","created":"2022-09-30","cited_by_count":14},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13},{"id":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12},{"id":"2412.09055","title":"Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images","created":"2024-12-12","cited_by_count":8},{"id":"2508.00395","title":"Decouple before Align: Visual Disentanglement Enhances Prompt Tuning","created":"2025-08-01","cited_by_count":7},{"id":"2508.17232","title":"Curvature Learning for Generalization of Hyperbolic Neural Networks","created":"2025-08-24","cited_by_count":4},{"id":"2506.21476","title":"Global and Local Entailment Learning for Natural World Imagery","created":"2025-06-26","cited_by_count":3},{"id":"2506.08906","title":"Hyperbolic Dual Feature Augmentation for Open-Environment","created":"2025-06-10","cited_by_count":2},{"id":"2506.18533","title":"Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces","created":"2025-06-23","cited_by_count":2},{"id":"2510.04770","title":"Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning","created":"2025-10-06","cited_by_count":1}],"next_cursor":null}