Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization

Inference

{"file name": "input.pdf", "number of pages": 31, "author": "Shizhe Xiang; Ke An; Wenlong Yu; Yue Liu; Jian Luan; Pei Fu; Qilong Wang", "title": "Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization", "creation date": null, "modification date": null, "kids": []}

Hardware

{"file name": "input.pdf", "number of pages": 31, "author": "Shizhe Xiang; Ke An; Wenlong Yu; Yue Liu; Jian Luan; Pei Fu; Qilong Wang", "title": "Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization", "creation date": null, "modification date": null, "kids": []}