D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI Paper • 2510.05684 • Published Oct 7 • 141
PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models Paper • 2506.00910 • Published Jun 1 • 10
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via texttt{D}ual-texttt{H}ead texttt{O}ptimization Paper • 2505.07675 • Published May 12 • 21