🔬 The Coolest Diffusion Research Isn't in LLMs — Evan Feinberg & Sergey Edunov, Genesis Molecular AI
Diffusion modelsProtein-ligand binding3D structure predictionDrug discovery pipelineSynthetic data generationReinforcement learningAgentic AI platformsADMET predictionBenchmarking in drug discoveryPharma partnershipsGPU bottlenecksHuman-AI collaboration
In this episode of Latent Space, Evan Feinberg and Sergey Edunov of Genesis Molecular AI discuss their pioneering work in applying diffusion models to protein-small molecule interactions for drug discovery. They explain how their foundation model, PEARL, achieves sub-angstrom accuracy in predicting 3D structures, enabling more effective drug design and integration with physical chemistry tools, while also exploring the challenges and future of AI-driven drug discovery including lab integration and agentic platforms.