ScholarGate
Asistent

Compară metode

Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.

Optimizarea Directă a Preferințelor×Autoencodere mascate×
DomeniuÎnvățare profundăÎnvățare profundă
FamilieMachine learningMachine learning
Anul apariției20232021
Autorul originalRafael RafailovKaiming He
TipTraining methodologyNeural network architecture
Sursa seminalăRafailov, 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. link ↗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). DOI ↗
Denumiri alternativeDPO, Direct preferenceMAE, Vision MAE
Înrudite44
RezumatDirect 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.
ScholarGateSet de date
  1. v1
  2. 1 Surse
  3. PUBLISHED
  1. v1
  2. 1 Surse
  3. PUBLISHED

Mergi la căutare Descarcă prezentarea

ScholarGateCompară metode: Direct Preference Optimization · Masked Autoencoders. Preluat la 2026-06-15 de pe https://scholargate.app/ro/compare