NEXUS: Bit-Exact ANN-to-SNN Equivalence via Neuromorphic Gate Circuits with Surrogate-Free Training
arxiv
The Condensate Theorem: Transformers are O(n), Not $O(n^2)$
arxiv
Metriplector: From Field Theory to Neural Architecture
arxiv
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
arxiv
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
semantic_scholar