9 papers
Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
Silen Naihin, Lev Stambler
Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Features that fire on token…
Towards Simple and Useful One-Time Programs in the Quantum Random Oracle Model
Lev Stambler
We construct simulation-secure one-time memories (OTM) in the random oracle model, and present a plausible argument for their security against quantum adversaries with bounded and…
A Note on Publicly Verifiable Quantum Money with Low Quantum Computational Resources
Fabrizio Genovese, Lev Stambler
In this work we present a publicly verifiable quantum money protocol which assumes close to no quantum computational capabilities. We rely on one-time memories which in turn can be…
New Quantum Internet Applications via Verifiable One-Time Programs
Lev Stambler
We introduce Verifiable One-Time Programs (Ver-OTPs) and use them to construct single-round Open Secure Computation (OSC), a novel primitive enabling applications like (1) single-r…
Effective Distance of Higher Dimensional HGPs and Weight-Reduced Quantum LDPC Codes
Shi Jie Samuel Tan, Lev Stambler
Quantum error correction plays a prominent role in the realization of quantum computation, and quantum low-density parity-check (qLDPC) codes are believed to be practically useful…
Provably Overwhelming Transformer Models with Designed Inputs
Lev Stambler, Seyed Sajjad Nezhadi, Matthew Coudron
We develop an algorithm which, given a trained transformer model as input, as well as a string of tokens of length and an integer , can genera…