{"total":113,"rows":[{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136,"area":null},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84,"area":null},{"id":"2110.13715","title":"ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60,"area":"lr"},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2110.14923","title":"Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones","created":"2021-10-28","cited_by_count":38,"area":null},{"id":"2101.00345","title":"Modeling Fine-Grained Entity Types with Box Embeddings","created":"2021-01-02","cited_by_count":36,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2201.06771","title":"TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters","created":"2022-01-18","cited_by_count":30,"area":null},{"id":"2211.15120","title":"Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings","created":"2022-11-28","cited_by_count":24,"area":null},{"id":"2108.02417","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","created":"2021-08-05","cited_by_count":23,"area":null},{"id":"2104.04597","title":"Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning","created":"2021-04-09","cited_by_count":22,"area":null},{"id":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2206.15478","title":"On the Learning and Learnability of Quasimetrics","created":"2022-06-30","cited_by_count":15,"area":null},{"id":"2210.08908","title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2109.05527","title":"Extracting Event Temporal Relations via Hyperbolic Geometry","created":"2021-09-12","cited_by_count":13,"area":null},{"id":"2207.06403","title":"3D Concept Grounding on Neural Fields","created":"2022-07-13","cited_by_count":13,"area":null},{"id":"2209.03648","title":"FETA: Towards Specializing Foundation Models for Expert Task Applications","created":"2022-09-08","cited_by_count":13,"area":null},{"id":"2406.10964","title":"Ontology Embedding: A Survey of Methods, Applications and Resources","created":"2024-06-16","cited_by_count":12,"area":null},{"id":"2409.19672","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","created":"2024-09-29","cited_by_count":12,"area":null},{"id":"2106.14361","title":"Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2405.12434","title":"Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference","created":"2024-05-21","cited_by_count":11,"area":null},{"id":"2106.08678","title":"Directed Graph Embeddings in Pseudo-Riemannian Manifolds","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2109.04997","title":"Box Embeddings: An open-source library for representation learning using geometric structures","created":"2021-09-10","cited_by_count":9,"area":null},{"id":"2110.14286","title":"TopicNet: Semantic Graph-Guided Topic Discovery","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2304.11949","title":"Geometric Relational Embeddings: A Survey","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2308.14009","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2503.06974","title":"Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment","created":"2025-03-10","cited_by_count":8,"area":null},{"id":"2105.04780","title":"Cross-Modal Generative Augmentation for Visual Question Answering","created":"2021-05-11","cited_by_count":7,"area":null},{"id":"2201.11794","title":"A Survey on Visual Transfer Learning using Knowledge Graphs","created":"2022-01-27","cited_by_count":7,"area":null},{"id":"2403.00435","title":"Hierarchical Indexing for Retrieval-Augmented Opinion Summarization","created":"2024-03-01","cited_by_count":7,"area":"rag"},{"id":"2510.08919","title":"PHyCLIP: $\\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning","created":"2025-10-10","cited_by_count":7,"area":"mllm"},{"id":"2402.14367","title":"Representation Learning for Frequent Subgraph Mining","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2205.00001","title":"Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2504.06135","title":"Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning","created":"2025-04-08","cited_by_count":4,"area":"rag"},{"id":"2507.03683","title":"On the rankability of visual embeddings","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2509.16411","title":"Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2207.03086","title":"Word Embedding for Social Sciences: An Interdisciplinary Survey","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2211.11033","title":"On the Complexity of Bayesian Generalization","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2304.14522","title":"Multivariate Representation Learning for Information Retrieval","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2305.15215","title":"Shadow Cones: A Generalized Framework for Partial Order Embeddings","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2403.17173","title":"Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.10924","title":"Binder: Hierarchical Concept Representation through Order Embedding of Binary Vectors","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2506.21476","title":"Global and Local Entailment Learning for Natural World Imagery","created":"2025-06-26","cited_by_count":3,"area":"mllm"},{"id":"2106.13549","title":"Connecting Sphere Manifolds Hierarchically for Regularization","created":"2021-06-25","cited_by_count":2,"area":null},{"id":"2203.05349","title":"Two-stream Hierarchical Similarity Reasoning for Image-text Matching","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2204.02058","title":"HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings","created":"2022-04-05","cited_by_count":2,"area":null},{"id":"2204.07476","title":"Guiding Attention using Partial-Order Relationships for Image Captioning","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2204.09268","title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2305.12027","title":"Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2305.15057","title":"Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.09670","title":"Probing Pretrained Language Models with Hierarchy Properties","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2406.15472","title":"Hyperbolic sentence representations for solving Textual Entailment","created":"2024-06-15","cited_by_count":2,"area":null},{"id":"2408.09715","title":"HYDEN: Hyperbolic Density Representations for Medical Images and Reports","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2503.19670","title":"fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models","created":"2025-03-25","cited_by_count":2,"area":"mllm"},{"id":"2508.21539","title":"HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2510.22538","title":"Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2603.22042","title":"Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2106.14431","title":"Modelling Monotonic and Non-Monotonic Attribute Dependencies with Embeddings: A Theoretical Analysis","created":"2021-06-28","cited_by_count":1,"area":null},{"id":"2111.12796","title":"Out-of-Category Document Identification Using Target-Category Names as Weak Supervision","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2210.16960","title":"Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunities","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2406.12020","title":"When Box Meets Graph Neural Network in Tag-aware Recommendation","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2411.12950","title":"NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning","created":"2024-11-20","cited_by_count":1,"area":"moe"},{"id":"2501.17518","title":"RegD: Hierarchical Embeddings via Dissimilarity between Arbitrary Euclidean Regions","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2507.20226","title":"Improving Subgraph Matching by Combining Algorithms and Graph Neural Networks","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2510.00394","title":"Graph2Region: Efficient Graph Similarity Learning with Structure and Scale Restoration","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2510.00402","title":"Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2606.06100","title":"HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.28336","title":"HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2609.06000","title":"ModularPhaseNet: Finite-Cyclic Phase Geometry for Computable Semantic Hierarchy, Direction, and Context Consistency in Standard Transformers","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2101.02158","title":"Order Embeddings from Merged Ontologies using Sketching","created":"2021-01-06","cited_by_count":0,"area":null},{"id":"2203.06937","title":"Modelling word learning and recognition using visually grounded speech","created":"2022-03-14","cited_by_count":0,"area":null},{"id":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2208.03317","title":"Image Quality Assessment: Learning to Rank Image Distortion Level","created":"2022-08-04","cited_by_count":0,"area":null},{"id":"2305.07163","title":"Lattice-preserving $\\mathcal{ALC}$ ontology embeddings with saturation","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2306.04133","title":"Answering Compositional Queries with Set-Theoretic Embeddings","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2405.16213","title":"Learning Visual-Semantic Subspace Representations","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2406.18579","title":"Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2412.08110","title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","created":"2024-12-11","cited_by_count":0,"area":"mllm"},{"id":"2505.12369","title":"Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations","created":"2025-05-18","cited_by_count":0,"area":"lr"},{"id":"2507.09487","title":"HMID-Net: An Exploration of Masked Image Modeling and Knowledge Distillation in Hyperbolic Space","created":"2025-07-13","cited_by_count":0,"area":"distill"},{"id":"2508.16687","title":"Native Hierarchical and Compositional Representations with Subspace Embeddings","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2510.13131","title":"OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2510.22897","title":"Charting the Design Space of Neural Graph Representations for Subgraph Matching","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2511.00641","title":"More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks","created":"2025-11-01","cited_by_count":0,"area":"inference"},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.21438","title":"PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.23136","title":"HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.01251","title":"Camouflage-aware Image-Text Retrieval via Expert Collaboration","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.16836","title":"Lorentz Framework for Semantic Segmentation","created":"2026-04-18","cited_by_count":0,"area":null}],"next_cursor":"100"}