เปรียบเทียบวิธี

	Direct Preference Optimization	[NEEDS TRANSLATION]
สาขาวิชา	การเรียนรู้เชิงลึก	การเรียนรู้เชิงลึก
ตระกูล	Machine learning	Machine learning
ปีกำเนิด	2023	2022
ผู้ริเริ่ม	Rafael Rafailov	Robin Rombach
ประเภท	Training methodology	Neural network architecture
แหล่งต้นตำรับ	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.	Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695).
ชื่อเรียกอื่น	DPO, Direct preference	LDM, Stable Diffusion, Latent Diffusion
ที่เกี่ยวข้อง	4	4
สรุป	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).	Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality.