{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"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":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2304.09172","title":"Hyperbolic Image-Text Representations","created":"2023-04-18","cited_by_count":136},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102},{"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":"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":"2505.23883","title":"BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning","created":"2025-05-29","cited_by_count":50},{"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":"2406.14496","title":"African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification","created":"2024-06-20","cited_by_count":32},{"id":"2501.15140","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","created":"2025-01-25","cited_by_count":31},{"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":"2302.06761","title":"Language Model Analysis for Ontology Subsumption Inference","created":"2023-02-14","cited_by_count":25},{"id":"2312.06323","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","created":"2023-12-11","cited_by_count":23},{"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":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19},{"id":"2504.14988","title":"Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation","created":"2025-04-21","cited_by_count":19},{"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":"2412.16418","title":"Revisiting MLLMs: An In-Depth Analysis of Image Classification Abilities","created":"2024-12-21","cited_by_count":15},{"id":"2309.07120","title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","created":"2023-09-13","cited_by_count":14},{"id":"2403.09207","title":"TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks","created":"2024-03-14","cited_by_count":14},{"id":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12},{"id":"2504.05457","title":"Taxonomy-Aware Evaluation of Vision-Language Models","created":"2025-04-07","cited_by_count":11},{"id":"2408.16176","title":"VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images","created":"2024-08-28","cited_by_count":10},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8},{"id":"2410.03052","title":"Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport","created":"2024-10-04","cited_by_count":3},{"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}],"next_cursor":null}