3 accepted papers
Contemporary AI safety is increasingly a full-stack discipline. It spans pretraining interventions, post-training alignment (instruction tuning, RLHF and preference-optimization variants), and deployment-time controls (guardrails, monitoring, and red-teaming). This paper argues these efforts optimiz…
Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However, algorithms that estimate state and state-action value functions typic…
Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadratically with respect to kernel size. In this paper, we present a parameter-free, FLOP-free "shift" operation as an alter…