Black Forest Labs' new Self-Flow technique makes training multimodal AI models 2.8x more efficient

This efficiency makes it viable for enterprises to move beyond generic off-the-shelf solutions and develop specialized models ...
IEEE

Routing-Oblivious and Data-Efficient Network Tomography with Flow-based Generative Model

Abstract: Given the high cost associated with directly measuring the Traffic Matrix (TM), researchers have devoted efforts to devising methods for estimating the complete TM from low-cost link loads ...
GitHub

Flexible MOF Generation with Torsion-Aware Flow Matching (MOFFlow-2)

mamba env create -f env.yml mamba activate mofflow-2 pip install git+https://github.com/microsoft/MOFDiff.git pip install -e . Note: If you want to build your own ...
GitHub

GitHub - clcarwin/float_Flow_Matching_Talking_Portrait: Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait.

This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. We shift the generative modeling from the pixel-based latent space to a ...
IEEE

Flow Matching Posterior Estimation for Simulation-Based Atmospheric Retrieval of Exoplanets

Abstract: The characterization of exoplanetary atmospheres allows a deeper understanding of planetary formation, evolution, and habitability through atmospheric retrieval, which consists in inferring ...