Michele Ronco

Evo 2 as a classification machine: evidence from in-context learning and mechanistic interpretability

This paper evaluates Evo 2's in-context learning capabilities on genomic sequences, finding strong performance on short sequences but degradation with length, and no benefit from model scaling.

Resolving power as a measure of protein stability prediction

The paper introduces resolving power as a metric for protein stability prediction, showing it correlates better with model performance than traditional benchmarks.