Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).
-
Updated
Jun 11, 2024 - Python
#
human-preference
Here are 3 public repositories matching this topic...
Video Generation Benchmark
video-understanding video-generation sora human-annotation text-to-video large-language-models llm multimodal-large-language-models preference-alignment video-evaluation video-generation-evaluation human-preference
-
Updated
Jun 9, 2025 - Python
Conditional VAE experiments: contextual bandit regret minimization and BERT-embedding human preference / reward prediction on WebGPT comparisons.
pytorch cvae variational-autoencoder contextual-bandit bert-embeddings reward-model human-preference
-
Updated
Aug 21, 2026 - Python
Add this topic to your repo
To associate your repository with the human-preference topic, visit your repo's landing page and select "manage topics."