Learning from Teacher Continuations at Student States
By regenerating prefixes from the evolving student, OLIVE continues improving after offline distillation plateaus while better preserving the general capabilities and plasticity of the student.
We have 2 of 143 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.
By regenerating prefixes from the evolving student, OLIVE continues improving after offline distillation plateaus while better preserving the general capabilities and plasticity of the student.
Preliminary results reveal substantial differences in safety-utility calibration across models and show that failures can emerge only after several initially safe interaction steps, motivating treating agent safety as a trajectory-level property rather than a single-turn or binary success criterion.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.