{"total":136,"rows":[{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"id":"2305.06611","title":"Hyperbolic Deep Learning in Computer Vision: A Survey","created":"2023-05-11","cited_by_count":73,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"area":null},{"id":"2410.04010","title":"Hyperbolic Fine-Tuning for Large Language Models","created":"2024-10-05","cited_by_count":27,"area":null},{"id":"2505.24722","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","created":"2025-05-30","cited_by_count":26,"area":null},{"id":"2412.05571","title":"A polar coordinate system represents syntax in large language models","created":"2024-12-07","cited_by_count":25,"area":null},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2405.19547","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","created":"2024-05-29","cited_by_count":20,"area":"mllm"},{"id":"2507.17787","title":"Hyperbolic Deep Learning for Foundation Models: A Survey","created":"2025-07-23","cited_by_count":20,"area":"mllm"},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2504.08896","title":"Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries","created":"2025-04-11","cited_by_count":18,"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":"2410.18857","title":"Probabilistic Language-Image Pre-Training","created":"2024-10-24","cited_by_count":16,"area":"mllm"},{"id":"2505.06934","title":"Whitened CLIP as a Likelihood Surrogate of Images and Captions","created":"2025-05-11","cited_by_count":16,"area":null},{"id":"2505.24623","title":"Hyperbolic Dataset Distillation","created":"2025-05-30","cited_by_count":15,"area":null},{"id":"2403.13015","title":"HyperVQ: MLR-based Vector Quantization in Hyperbolic Space","created":"2024-03-18","cited_by_count":13,"area":null},{"id":"2404.05016","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","created":"2024-04-07","cited_by_count":12,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2404.00974","title":"Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping","created":"2024-04-01","cited_by_count":11,"area":null},{"id":"2408.05097","title":"Hyperbolic Learning with Multimodal Large Language Models","created":"2024-08-09","cited_by_count":10,"area":"mllm"},{"id":"2408.14435","title":"Social Perception of Faces in a Vision-Language Model","created":"2024-08-26","cited_by_count":10,"area":"mllm"},{"id":"2308.13279","title":"Hyperbolic Random Forests","created":"2023-08-25","cited_by_count":9,"area":null},{"id":"2403.00372","title":"HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation","created":"2024-03-01","cited_by_count":8,"area":null},{"id":"2407.18145","title":"Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2411.17490","title":"Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2310.13841","title":"Fast hyperboloid decision tree algorithms","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2409.02599","title":"A Fashion Item Recommendation Model in Hyperbolic Space","created":"2024-09-04","cited_by_count":7,"area":null},{"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,"area":null},{"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":"2404.19228","title":"Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric","created":"2024-04-30","cited_by_count":6,"area":null},{"id":"2409.13079","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","created":"2024-09-19","cited_by_count":6,"area":null},{"id":"2502.17130","title":"Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2602.23058","title":"GeoWorld: Geometric World Models","created":"2026-02-26","cited_by_count":6,"area":"wm"},{"id":"2407.09686","title":"SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2410.16813","title":"Klein Model for Hyperbolic Neural Networks","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2505.21228","title":"Is Hyperbolic Space All You Need for Medical Anomaly Detection?","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.10710","title":"Continual Hyperbolic Learning of Instances and Classes","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2510.20322","title":"HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models","created":"2025-10-23","cited_by_count":5,"area":"mllm"},{"id":"2510.21441","title":"OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields","created":"2025-10-24","cited_by_count":5,"area":null},{"id":"2602.18858","title":"Hyperbolic Busemann Neural Networks","created":"2026-02-21","cited_by_count":5,"area":null},{"id":"2401.15478","title":"Product Manifold Representations for Learning on Biological Pathways","created":"2024-01-27","cited_by_count":4,"area":null},{"id":"2403.06295","title":"A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets","created":"2024-03-10","cited_by_count":4,"area":null},{"id":"2411.17784","title":"HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2506.05826","title":"Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2507.03683","title":"On the rankability of visual embeddings","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2602.20479","title":"Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation","created":"2026-02-24","cited_by_count":4,"area":"diffusion"},{"id":"2310.09247","title":"Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy","created":"2023-10-13","cited_by_count":3,"area":"diffusion"},{"id":"2412.01495","title":"Adversarial Attacks on Hyperbolic Networks","created":"2024-12-02","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":"2510.27391","title":"Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds","created":"2025-10-31","cited_by_count":3,"area":"mllm"},{"id":"2511.15633","title":"Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","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":"2503.02248","title":"Making Better Mistakes in CLIP-Based Zero-Shot Classification with Hierarchy-Aware Language Prompts","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2506.16398","title":"HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2508.15480","title":"Learning Protein-Ligand Binding in Hyperbolic Space","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.15508","title":"Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2511.18808","title":"HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations","created":"2025-11-24","cited_by_count":2,"area":"rag"},{"id":"2601.19597","title":"The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence","created":"2026-01-27","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":"2608.09572","title":"Hyperbolic Multimodal Continual Learning","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2407.13567","title":"Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2502.12481","title":"Predicate Hierarchies Improve Few-Shot State Classification","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.00804","title":"DELST: Dual Entailment Learning for Hyperbolic Image-Gene Pretraining in Spatial Transcriptomics","created":"2025-03-02","cited_by_count":1,"area":null},{"id":"2503.15166","title":"Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU","created":"2025-03-19","cited_by_count":1,"area":"safety"},{"id":"2504.01386","title":"DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.14875","title":"ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2506.10146","title":"Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2511.12020","title":"LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2511.20679","title":"Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2511.21092","title":"MNM : Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.20029","title":"$\\text{H}^2$em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.04614","title":"HyperAlign: Hyperbolic Entailment Cones for Adaptive Text-to-Image Alignment Assessment","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2602.02533","title":"HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models","created":"2026-01-28","cited_by_count":1,"area":"vla"},{"id":"2602.07739","title":"HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation","created":"2026-02-08","cited_by_count":1,"area":"rag"},{"id":"2602.11448","title":"Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2603.23311","title":"ARGENT: Adaptive Hierarchical Image-Text Representations","created":"2026-03-24","cited_by_count":1,"area":"mllm"},{"id":"2604.18867","title":"Hierarchically Robust Zero-shot Vision-language Models","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2605.05054","title":"Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation","created":"2026-05-06","cited_by_count":1,"area":"mllm"},{"id":"2605.08874","title":"Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation","created":"2026-05-09","cited_by_count":1,"area":"mllm"},{"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":"2606.31245","title":"HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2607.23335","title":"The Gate Always Closes: On Injecting Auxiliary Signals into Frozen Vision-Language Models","created":"2026-07-25","cited_by_count":1,"area":"mllm"},{"id":"2311.05784","title":"Are \"Hierarchical\" Visual Representations Hierarchical?","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2410.16698","title":"Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2411.16236","title":"DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2503.01184","title":"Language-Assisted Feature Transformation for Anomaly Detection","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.10889","title":"Fine-Grained Rib Fracture Diagnosis with Hyperbolic Embeddings: A Detailed Annotation Framework and Multi-Label Classification Model","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2505.09997","title":"Descriptive Image-Text Matching with Graded Contextual Similarity","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.04764","title":"HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place Recognition","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.19389","title":"Emergence of Text Readability in Vision Language Models","created":"2025-06-24","cited_by_count":0,"area":"mllm"},{"id":"2508.16744","title":"Hyperbolic Multimodal Representation Learning for Biological Taxonomies","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.12771","title":"Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.24655","title":"HyperHELM: Hyperbolic Hierarchy Encoding for mRNA Language Modeling","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","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"}],"next_cursor":"100"}