4 papers
StateSync-GKR: Design and Evaluation of a Reusable Sparse GKR Engine
Jinwook Kim
Authenticated state transitions need proof engines that conserve memory, avoid repeated setup, keep every result bound to its request under parallel execution and return complete p…
In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?
Ben Bucknall, Saad Siddiqui, Lara Thurnherr +19
International cooperation is common in AI research, including between geopolitical rivals. While many experts advocate for greater international cooperation on AI safety to address…
Beyond the Boundaries of Proximal Policy Optimization
Charlie B. Tan, Edan Toledo, Benjamin Ellis +2
Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed in…
Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
Anna Mészáros, Szilvia Ujváry, Wieland Brendel +2
LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attribut…