{"list":"other","total":68,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300},{"id":"2004.00849","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","created":"2020-04-02","cited_by_count":288},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"1804.03329","title":"Representation Tradeoffs for Hyperbolic Embeddings","created":"2018-04-10","cited_by_count":206},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132},{"id":"2011.11765","title":"Boosting Contrastive Self-Supervised Learning with False Negative Cancellation","created":"2020-11-23","cited_by_count":119},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108},{"id":"2203.05898","title":"Hyperbolic Image Segmentation","created":"2022-03-11","cited_by_count":102},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90},{"id":"2303.13440","title":"CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not","created":"2023-03-23","cited_by_count":79},{"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":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","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":"2106.03719","title":"Incremental False Negative Detection for Contrastive Learning","created":"2021-06-07","cited_by_count":48},{"id":"2106.03306","title":"HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections","created":"2021-06-07","cited_by_count":47},{"id":"2212.01758","title":"Improving Zero-shot Generalization and Robustness of Multi-modal Models","created":"2022-12-04","cited_by_count":45},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43},{"id":"2311.17518","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding","created":"2023-11-29","cited_by_count":29},{"id":"2403.18978","title":"TextCraftor: Your Text Encoder Can be Image Quality Controller","created":"2024-03-27","cited_by_count":27},{"id":"2410.04010","title":"Hyperbolic Fine-Tuning for Large Language Models","created":"2024-10-05","cited_by_count":27},{"id":"2505.24722","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","created":"2025-05-30","cited_by_count":26},{"id":"2504.01916","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","created":"2025-04-02","cited_by_count":23},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19},{"id":"2412.01023","title":"Learning Structured Representations with Hyperbolic Embeddings","created":"2024-12-02","cited_by_count":16},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12},{"id":"2504.08912","title":"HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules","created":"2025-04-11","cited_by_count":12},{"id":"2312.06112","title":"MAFA: Managing False Negatives for Vision-Language Pre-training","created":"2023-12-11","cited_by_count":11},{"id":"2411.17490","title":"Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval","created":"2024-11-26","cited_by_count":8},{"id":"2508.11176","title":"Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter Learning","created":"2025-08-15","cited_by_count":8},{"id":"2507.10095","title":"FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text","created":"2025-07-14","cited_by_count":7},{"id":"2310.08390","title":"Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning","created":"2023-10-12","cited_by_count":3},{"id":"2511.06653","title":"HiMo-CLIP: Modeling Semantic Hierarchy and Monotonicity in Vision-Language Alignment","created":"2025-11-10","cited_by_count":2},{"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},{"id":"2602.14490","title":"Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts","created":"2026-02-16","cited_by_count":1}],"next_cursor":null}