Track 4 · Path · 4 explainers
Generative AI
Diffusion models, RLHF, LoRA, and retrieval-augmented generation
- 1
Diffusion Models
Generate images by learning to reverse a gradual noising process
- 2
Retrieval-Augmented Generation
Ground language model outputs in retrieved documents to reduce hallucination
- 3
LoRA & Parameter-Efficient Fine-Tuning
Adapt large models by training tiny low-rank matrices instead of all the weights
- 4
RLHF
Align language models with human preferences using reward models and policy optimization