Bandingkan kaedah
Semak kaedah pilihan anda secara bersebelahan; baris yang berbeza akan diserlahkan.
| Direct Preference Optimization× | Mamba (Model Ruang Keadaan)× | Autoenkoder Bertopeng× | |
|---|---|---|---|
| Bidang | Pembelajaran Mendalam | Pembelajaran Mendalam | Pembelajaran Mendalam |
| Keluarga | Machine learning | Machine learning | Machine learning |
| Tahun asal≠ | 2023 | 2023 | 2021 |
| Pengasas≠ | Rafael Rafailov | Albert Gu | Kaiming He |
| Jenis≠ | Training methodology | Neural network architecture | Neural network architecture |
| Sumber perintis≠ | 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. link ↗ | Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956. 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 ↗ |
| Alias≠ | DPO, Direct preference | Mamba, State space models, Selective state space | MAE, Vision MAE |
| Berkaitan | 4 | 4 | 4 |
| Ringkasan≠ | 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). | Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power. | 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 data ↗ |
|
|
|