{"list":"other","total":57,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"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":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2208.05868","title":"TotalSegmentator: robust segmentation of 104 anatomical structures in CT images","created":"2022-08-11","cited_by_count":613},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"2507.05201","title":"MedGemma Technical Report","created":"2025-07-07","cited_by_count":436},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237},{"id":"2506.07044","title":"Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning","created":"2025-06-08","cited_by_count":230},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212},{"id":"2406.19280","title":"HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale","created":"2024-06-27","cited_by_count":200},{"id":"2403.17834","title":"Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","created":"2024-03-26","cited_by_count":199},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2402.09181","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","created":"2024-02-14","cited_by_count":184},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"2404.00578","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","created":"2024-03-31","cited_by_count":162},{"id":"2403.19046","title":"LITA: Language Instructed Temporal-Localization Assistant","created":"2024-03-27","cited_by_count":125},{"id":"2502.09838","title":"HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation","created":"2025-02-14","cited_by_count":114},{"id":"2308.09442","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","created":"2023-08-18","cited_by_count":100},{"id":"2403.06801","title":"CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging","created":"2024-03-11","cited_by_count":96},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72},{"id":"2501.14548","title":"Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding","created":"2025-01-24","cited_by_count":54},{"id":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46},{"id":"2310.18341","title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","created":"2023-10-22","cited_by_count":37},{"id":"2501.04678","title":"RadGPT: Constructing 3D Image-Text Tumor Datasets","created":"2025-01-08","cited_by_count":36},{"id":"2508.08224","title":"Capabilities of GPT-5 on Multimodal Medical Reasoning","created":"2025-08-11","cited_by_count":36},{"id":"2303.09187","title":"PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers","created":"2023-03-16","cited_by_count":32},{"id":"2506.11147","title":"3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks","created":"2025-06-11","cited_by_count":26},{"id":"2208.03012","title":"Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution","created":"2022-08-05","cited_by_count":25},{"id":"2504.13650","title":"EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model","created":"2025-04-18","cited_by_count":22},{"id":"2509.09254","title":"Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis","created":"2025-09-11","cited_by_count":18},{"id":"2411.12783","title":"Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model","created":"2024-11-19","cited_by_count":15},{"id":"2408.11965","title":"CT-AGRG: Automated Abnormality-Guided Report Generation from 3D Chest CT Volumes","created":"2024-08-21","cited_by_count":10},{"id":"2412.12661","title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","created":"2024-12-17","cited_by_count":6},{"id":"2509.13175","title":"More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era","created":"2025-09-16","cited_by_count":6},{"id":"2403.05141","title":"Med3DInsight: Enhancing 3D Medical Image Understanding with 2D Multi-Modal Large Language Models","created":"2024-03-08","cited_by_count":5}],"next_cursor":null}