Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
NeurIPSSpotlight2025
TL;DR
Numerous well-established studies have demonstrated the superhuman capabilities of modern Vision-Language Models (VLMs) across a wide range of tasks…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
vision-language generalization language model robustness alignment
← All NeurIPS 2025 Spotlight papers · Browse the whole archive