AI RESEARCH
Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues
arXiv CS.CV
•
ArXi:2603.21138v1 Announce Type: new Recent advances in zero-shot learning (ZSL) have nstrated the potential of generative models. Typically, generative ZSL synthesizes visual features conditioned on semantic prototypes to model the data distribution of unseen classes, followed by