ScholarGate
Trợ lý

So sánh phương pháp

Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.

QLoRA×Direct Preference Optimization×Mô hình Khuếch tán Tiềm ẩn×
Lĩnh vựcHọc sâuHọc sâuHọc sâu
HọMachine learningMachine learningMachine learning
Năm ra đời202320232022
Người khởi xướngTim DettmersRafael RafailovRobin Rombach
LoạiTraining methodologyTraining methodologyNeural network architecture
Công trình gốcDettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗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 ↗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). DOI ↗
Tên gọi khácQLoRA, Quantized LoRADPO, Direct preferenceLDM, Stable Diffusion, Latent Diffusion
Liên quan444
Tóm tắtQLoRA is an efficient fine-tuning method introduced by Dettmers et al. in 2023 that enables fine-tuning large language models using quantization and low-rank adaptation. By combining 4-bit quantization with LoRA, QLoRA reduces memory requirements by 75%, enabling fine-tuning of 65B-parameter models on single GPUs.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.
ScholarGateBộ dữ liệu
  1. v1
  2. 1 Nguồn tài liệu
  3. PUBLISHED
  1. v1
  2. 1 Nguồn tài liệu
  3. PUBLISHED
  1. v1
  2. 1 Nguồn tài liệu
  3. PUBLISHED

Đến trang tìm kiếm Tải xuống bản trình chiếu

ScholarGateSo sánh phương pháp: QLoRA · Direct Preference Optimization · Latent Diffusion Models. Truy cập ngày 2026-06-18 từ https://scholargate.app/vi/compare