{"total":20,"rows":[{"id":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"id":"2412.13126","title":"Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis","created":"2024-12-17","cited_by_count":21,"area":"mllm"},{"id":"2504.10568","title":"AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark","created":"2025-04-14","cited_by_count":16,"area":"mllm"},{"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,"area":"mllm"},{"id":"2505.07019","title":"A Vision-Language Foundation Model for Leaf Disease Identification","created":"2025-05-11","cited_by_count":6,"area":"mllm"},{"id":"2403.15836","title":"VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image Classification","created":"2024-03-23","cited_by_count":5,"area":"mllm"},{"id":"2602.13662","title":"LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases","created":"2026-02-14","cited_by_count":5,"area":"mllm"},{"id":"2509.03800","title":"MedVista3D: Vision-Language Modeling for Reducing Diagnostic Errors in 3D CT Disease Detection, Understanding and Reporting","created":"2025-09-04","cited_by_count":4,"area":"mllm"},{"id":"2603.00431","title":"Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models","created":"2026-02-28","cited_by_count":4,"area":"mllm"},{"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":"2603.07294","title":"MAviS: A Multimodal Conversational Assistant For Avian Species","created":"2026-03-07","cited_by_count":2,"area":"mllm"},{"id":"2512.21126","title":"MarineEval: Assessing the Marine Intelligence of Vision-Language Models","created":"2025-12-24","cited_by_count":1,"area":"mllm"},{"id":"2609.11916","title":"Can Edge-Deployable Vision-Language Models Identify Species?","created":"2026-09-10","cited_by_count":1,"area":"mllm"},{"id":"2512.15748","title":"Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors","created":"2025-12-10","cited_by_count":0,"area":"mllm"},{"id":"2604.16785","title":"Bridging Coarse and Fine Recognition: A Hybrid Approach for Open-Ended Multi-Granularity Object Recognition in Interactive Educational Games","created":"2026-04-18","cited_by_count":0,"area":"mllm"},{"id":"2605.03259","title":"CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2607.02909","title":"Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2609.03985","title":"IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish Recognition","created":"2026-09-03","cited_by_count":0,"area":"mllm"},{"id":"2609.22897","title":"Scout: Open-World Species Recognition on the Edge","created":"2026-09-19","cited_by_count":0,"area":"mllm"}],"next_cursor":null}