Diffusion Generates Distinct Structures While Regression Averages Them
Gabriele Corso · 🔬Generating Molecules, Not Just Models · Feb 12, 2026 · at 25:44
Gabriele Corso explains the architectural shift from regression to generative diffusion in biomolecular structure prediction.
0:00 / 0:22exact quote · 22.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“What's going to happen in a regression model is that, you know, I'm going to try to make an average of those different kind of answers that I had in mind. When you have a generative model, what you're going to do is, you know, sample all these different answers, and then maybe Use a separate models to analyze those different answers and pick out the best.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Gabriele Corso
Specialized Equivariant Architectures Vastly Outperform Simple Transformers in Molecular ML
“This field is one of the I would argue very few fields in applied machine learning where we still have kind of architecture. They are Very specialized. And, you know, there are many people that have tried to replace these architectures with, you know, simple t…”
Boltz-1 Was the First Open-Source Model Matching AlphaFold 3 Accuracy
“We went ahead and built Pulse One, which was the first fully open source kind of model to approach the level of accuracy of half-fold-free.”
Generative Molecular Models Exhibit Dramatic Inference-Time Compute Scaling
“These days we're seeing kind of pretty dramatic inference time scaling of these models where, you know, the more you run them, the better the results are.”
Model Structural Confidence Is a Poor Predictor of Binding Affinity
“Unfortunately, confidence is not a very good predictor of affinity.”
Most Protein Design Validation Uses Targets With Training Data Overlap
“One of the things that, you know, we found, ah, with the field was that a lot of the validation, especially outside of the validation that was done on specific problems, was done on targets that have a lot of, you know, known interactions in, in the training d…”