← all releases
Bowang Lab·Feb 2, 2026·Not specified·open source
EchoJEPA
EchoJEPA is a latent predictive foundation model for echocardiography, trained on 18 million echocardiograms across 300,000 patients. It aims to reduce annotation burden and improve diagnostic consistency by learning generalizable representations from large unlabeled video archives. ([arxiv.org](https://arxiv.org/abs/2602.02603?utm_source=openai))
BioLLMsLLM
overview
EchoJEPA is a latent predictive foundation model for echocardiography, trained on 18 million echocardiograms across 300,000 patients. It aims to reduce annotation burden and improve diagnostic consistency by learning generalizable representations from large unlabeled video archives. ([arxiv.org](https://arxiv.org/abs/2602.02603?utm_source=openai))
key features
- 01Latent predictive modeling for echocardiography
- 02Trained on 18 million echocardiograms
- 03Reduces left ventricular ejection fraction estimation error by 19%
- 04Achieves 87.4% view classification accuracy
- 05Strong sample efficiency with only 1% labeled data
related productsbrowse all →
Protenixopen sourceProtenix is an open-source, trainable PyTorch implementation of AlphaFold 3, designed for high-accuracy biomolecular structure prediction. It aims to advance accessible and extensible research tools for the computational biology community. ([github.com](https://github.com/bytedance/Protenix?utm_source=openai))Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.Z-Imageopen sourceZ-Image is an efficient image generation foundation model developed by Tongyi-MAI, designed to produce high-quality, diverse, and stylistically versatile images. It serves as a robust base for creators, researchers, and developers seeking advanced image generation capabilities.