So sánh phương pháp

	Direct Preference Optimization	Mô hình Tự mã hóa Che giấu
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2023	2021
Người khởi xướng	Rafael Rafailov	Kaiming He
Loại	Training methodology	Neural network architecture
Công trình gốc	Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023). Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290.	He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009).
Tên gọi khác	DPO, Direct preference	MAE, Vision MAE
Liên quan	4	4
Tóm tắt	Direct Preference Optimization (DPO) is a training method introduced by Rafailov et al. in 2023 that aligns language models with human preferences without requiring an explicit reward model. By directly optimizing for preference pairs (better response vs worse response), DPO simplifies the training pipeline compared to reinforcement learning from human feedback (RLHF).	Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.