We have 4 of 11 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled evaluations across the AI industry, agents trained to maximize reward have accessed unauthorized information, attempted to evade monitoring s...
It is shown that adding more agents is not a sufficient defense, because the adversary can simply scale with the group, and that allowing deceivers to coordinate privately can make them less effective.
SportD opens a new direction for rigorously evaluating physical strategic decision-making in VLMs, showing that careful decomposition of their choices can reveal the mechanisms underlying systematic biases such as risk aversion.
A multimodal gap is revealed in how foundation models express meaning, and how their understanding may not transfer faithfully nor equally across modalities.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
