Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
18 papers published across 0 labs.
This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.
This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.
Dissociation suggests current neuron-level monosemanticity metrics are insensitive to a class of real interpretability gains, and positions cheap architectural priors as a viable training-time complement to post-hoc tooling.