Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Learning Lookahead Lemmas for Neural Network Verification
Liam Davis, Haoze Wu
State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism. We introduce an inprocessing framework for neural network verification…
cs.LG2026
Lookahead Branching for Neural Network Verification
Liam Davis, Duo Zhou, Huan Zhang +3
In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bou…
cs.LG2026
Lattice Deduction Transformers
Liam Davis, Leopold Haller, Alberto Alfarano +1
We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent state through a lattice between f…