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 generalist neuroimaging vision foundation model pretrained on 5.24M clinical MRI and CT volumes for radiologic diagnosis and report generation.

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.

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.

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 multimodal vision-text foundation model for brain CT and MRI, pretrained on ~10M paired images and reports to act as a clinical copilot across seven imaging tasks.

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

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

A multimodal LLM fine-tuned to interpret electrocardiogram images, trained on the >1M-sample ECGInstruct dataset and evaluated on the ECGBench benchmark.

A multimodal ECG-language model that aligns 12-lead ECG waveforms with clinical text for conversational cardiac diagnosis and automated report generation.

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.

A 40B-parameter generalist medical vision-language foundation model spanning radiology, pathology, dermatology, retinography, and endoscopy.

A multimodal large language model for 3D medical imaging, handling retrieval, report generation, VQA, positioning, and segmentation on CT volumes.

An instruction-tuned vision-language foundation model from Stanford for interpreting and summarizing chest X-rays across eight clinical task types.

Hierarchical knowledge-enhanced vision-language pre-training model for universal brain MRI diagnosis across 10+ diseases from multi-modal scans and reports.

A generalist radiology foundation model that handles interleaved 2D and 3D medical scans with text for diagnosis, VQA, and report generation.

A multimodal generative AI assistant for pathology, pairing the PathCLIP vision encoder with a Vicuna-13B LLM and a toolkit of eight pathology-specific models.

Prompt-based medical vision-language pretraining that unifies fusion-encoder and dual-encoder architectures, handling image-only, text-only, and image-text inputs in one model.