← Search

Arda Uzunoglu

2 accepted papers

2026

Trust Functions: Near Lossless Weak-to-Strong Generalization by Learning to Trust the Weak Teacher

ICML 2026poster

Weak-to-strong generalization studies how to improve a strong student using supervision from a weaker teacher when reliable labels are scarce. We view this primarily as a data selection problem, where the key challenge is to identify which weak labels are reliable enough to serve as a training signa…

Cited by 0SourceScholar
2026

WoW!: World Models in a Closed-Loop World

ICLR 2026oral

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchma…

Cited by 0SourcecodeScholar