7 papers
Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning
Andrea Silvi, Ponrawee Prasertsom, Jennifer Culbertson +3
Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. Following prior work that relate…
Learning Contextual Runtime Monitors for Safe AI-Based Autonomy
Alejandro Luque-Cerpa, Mengyuan Wang, Emil Carlsson +3
We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomou…
FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference
Wilhelm Tranheden, Shahnawaz Ahmed, Devdatt Dubhashi +2
Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabula…
PACE: Procedural Abstractions for Communicating Efficiently
Jonathan D. Thomas, Andrea Silvi, Devdatt Dubhashi +1
A central but unresolved aspect of problem-solving in AI is the capability to introduce and use abstractions, something humans excel at. Work in cognitive science has demonstrated…
Recursive numeral systems are highly regular and easy to process
Ponrawee Prasertsom, Andrea Silvi, Jennifer Culbertson +3
Much recent work has shown how cross-linguistic variation is constrained by competing pressures from efficient communication. However, little attention has been paid to the role of…
Variational Quantum Optimization with Continuous Bandits
Marc Wanner, Johan Jonasson, Emil Carlsson +1
We introduce a novel approach to variational Quantum algorithms (VQA) via continuous bandits. VQA are a class of hybrid Quantum-classical algorithms where the parameters of Quantum…