Explore the Mirror Langevin Diffusions, a groundbreaking family of diffusions introduced in machine learning contexts during 2020/21, in this 36-minute lecture from the Workshop on "Probabilistic Mass Transport - from Schrödinger to Stochastic Analysis." Discover how these diffusions represent Langevin diffusions on Hessian manifolds and understand their fundamental nature comparable to Euclidean Langevin diffusions. Learn about the connections between Mirror Langevin Diffusions and various contemporary mathematical topics including Wasserstein gradient flows, Schrödinger bridges, Sinkhorn algorithms, and sampling techniques. Gain insight into this emerging field where many key properties remain to be discovered, making it an active area of mathematical research with significant implications for machine learning and stochastic analysis.