A Phenomenology of Neural Geometry in Vision-Language-Action Models
Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability.
We have 2 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.
Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability.
This work finds that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max, and provides evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.