Protein folding models have always used recycling — effectively recurrent depth with stop grad
amyxlu · x · 2026-09-03
A concise architecture observation: protein folding models like AlphaFold have always used recycling, which is essentially recurrent depths / looped transformers with a stop gradient applied across iterations.
More from Research
- Counterfactual Debugging: causal attribution over 1M steps to localize sim2real gaps in world-model agents — MichaelD1729 · 2026-09-03
- DeepMind's 83-Page Study: Autonomous Research Agents Fabricate 90% of Findings — williamtp · 2026-09-03
- How Google's RT-2 triggered the robotics boom: Understanding AI explains VLA models — binarybits · 2026-09-03
- Goodfire chief scientist Tom McGrath on interpretability: SAEs may fracture what networks really learn — Machine Learning Street Talk · 2026-09-03
- CBAI opens Fall AI Safety fellowship: $15k stipend, 10 weeks in Boston — benno_krojer · 2026-09-03
- What 12 million empirical research results can teach us — RexDouglass · 2026-09-03