{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"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":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102},{"id":"1911.08411","title":"Mixed-curvature Variational Autoencoders","created":"2019-11-19","cited_by_count":86},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74},{"id":"2107.11472","title":"Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers","created":"2021-07-23","cited_by_count":57},{"id":"2203.03825","title":"Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification","created":"2022-03-08","cited_by_count":52},{"id":"1306.6802","title":"Evaluation Measures for Hierarchical Classification: a unified view and novel approaches","created":"2013-06-28","cited_by_count":46},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41},{"id":"2201.03194","title":"Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification","created":"2022-01-10","cited_by_count":29},{"id":"2401.11374","title":"Language Models as Hierarchy Encoders","created":"2024-01-21","cited_by_count":28},{"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":"2503.08250","title":"Aligning Text to Image in Diffusion Models is Easier Than You Think","created":"2025-03-11","cited_by_count":22},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","cited_by_count":21},{"id":"2311.14064","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","created":"2023-11-23","cited_by_count":21},{"id":"2503.12797","title":"KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding","created":"2025-03-17","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":"2306.11180","title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","created":"2023-06-19","cited_by_count":18},{"id":"2412.14695","title":"Lorentzian Residual Neural Networks","created":"2024-12-19","cited_by_count":17},{"id":"2406.11608","title":"Visually Consistent Hierarchical Image Classification","created":"2024-06-17","cited_by_count":16},{"id":"2412.01023","title":"Learning Structured Representations with Hyperbolic Embeddings","created":"2024-12-02","cited_by_count":16},{"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":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12},{"id":"2503.08253","title":"SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models","created":"2025-03-11","cited_by_count":11},{"id":"2408.05097","title":"Hyperbolic Learning with Multimodal Large Language Models","created":"2024-08-09","cited_by_count":10},{"id":"2412.09055","title":"Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images","created":"2024-12-12","cited_by_count":8},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8},{"id":"2505.24840","title":"The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition","created":"2025-05-30","cited_by_count":7},{"id":"2512.15885","title":"Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models","created":"2025-12-17","cited_by_count":5},{"id":"2508.17232","title":"Curvature Learning for Generalization of Hyperbolic Neural Networks","created":"2025-08-24","cited_by_count":4},{"id":"2410.03052","title":"Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport","created":"2024-10-04","cited_by_count":3},{"id":"2510.27391","title":"Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds","created":"2025-10-31","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}],"next_cursor":null}