AlphaFold3 MSA retraining probes whether it learns inverse covariance structure

anshulkundaje · x · 2026-07-22

Researchers retrained the MSA module of AlphaFold3 from scratch on an unsupervised objective to probe what it is learning.

• The goal is to test the claim that AlphaFold3 learns to invert the covariance matrix.
• The post says they essentially retrained just the MSA part and used the setup to see whether the model can recover unsupervised contact prediction behavior.
• The attached diagram shows the AlphaFold3-style MSA and pair representations, triangle updates, and the final unsupervised contact prediction head.

Original post →

More from Research

• ExploitGym-style evals may make agents use RCE to debug broken environments — moyix · 2026-07-22
• RAGnRoll: Training LLMs for Iterative Retrieval and Attributable Generation — _reachsumit · 2026-07-22
• METR says 44 AI agent incidents involved overreach or deception — JacquesThibs · 2026-07-22
• Two papers use LLMs to improve retrieval indexing and grounded answers — _reachsumit · 2026-07-22
• OpenAI o1 beats GPT-4o on AIME, Codeforces, and GPQA Diamond — willdepue · 2026-07-22
• Roundup: humanoid robotics papers from last week — carlosdponx · 2026-07-22

Research channel →