All Competitors

A 3D vision-language foundation model for abdominal CT that pretrains on paired scans, radiology reports, and structured EHR codes for zero-shot interpretation.

A medical vision-language model that accepts visual-referring multimodal input and produces pixel-grounded multimodal output, jointly answering and segmenting medical images.

A family of CNN foundation models pretrained on ~1.9M multimodal radiology images for transfer learning across medical imaging tasks.

A 4.2B-parameter lightweight biomedical vision-language assistant built on Phi-2 that outperforms larger LLaVA-Med models on medical visual question answering.

Medical multimodal LLM (2B and 8B) trained for generalizable, step-by-step clinical reasoning via Mentor-Intern Collaborative Search.

A generalist medical multimodal LLM built on Qwen2.5-VL for unified medical image understanding, visual question answering, report generation, and clinical reasoning across 12+ imaging modalities.

Universal foundation model that jointly generates diagnostic text and segments the corresponding targets across ten biomedical imaging modalities.

A reinforcement-learning-enhanced general medical vision-language model that adds step-by-step reasoning for medical image diagnosis and visual question answering.

A reinforcement-learning-trained medical vision-language model for generalizable reasoning across eight imaging modalities and five clinical question types.

A 2B-parameter medical vision-language model that uses reinforcement learning (GRPO) to produce explicit, human-interpretable reasoning for radiology visual question answering.

Lightweight 7B vision-language foundation model from Microsoft Research, released research-only under the Microsoft Research License, that generates radiology findings from chest X-rays.

Medical large vision-language model unifying image comprehension and generation in one autoregressive framework via heterogeneous LoRA knowledge adaptation.

Multimodal multitask foundation model that fuses 3D low-dose chest CT with clinical data to perform 17 lung-cancer-screening tasks via free-text question answering.

A self-improving text-to-image diffusion foundation model that generates synthetic medical images across multiple modalities and organs to augment downstream clinical AI tasks.

A Segment Anything Model (SAM) variant finetuned on diverse medical images, delivering a reusable promptable checkpoint for interactive and automatic medical image segmentation.

Biomedical multimodal LLM with pixel-level insight, combining visual question answering, pixel-grounded prompts, and segmentation via a mixture-of-experts design.

A bilingual (Arabic-English) bio-medical large multimodal model built on Llama 3.1 for medical image understanding and clinical text conversation.

A biomedical foundation model for joint segmentation, detection, and recognition across nine imaging modalities using natural language prompts.

Self-supervised vision transformer pretrained on chest X-rays to produce a domain-specific foundation model for classification and lung segmentation.

Region-aware bilingual (Chinese-English) medical multimodal LLM that handles image- and region-level vision-language tasks across eight imaging modalities.

A general CT image segmentation foundation model that uses task-prompted automatic pathway decoding to segment 83 anatomical structures and lesions across whole-body CT.

A masked contrastive chest X-ray foundation model that aligns radiograph patches with report text for zero-shot and fine-grained diagnosis.

Open-source, lightweight generalist vision-language foundation model for diverse biomedical imaging and text tasks.

A medical multimodal large language model pretrained on the 25M-image MedTrinity-25M dataset, achieving state-of-the-art accuracy on biomedical visual question answering.