zhaoyl18
Follow
-
-
-
-
SVDD Public
Forked from masa-ue/SVDDDerivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (+ images)
Python UpdatedOct 3, 2024 -
SVDD-image Public
Forked from masa-ue/SVDD-imageDerivative-Free, Training-Free, Guidance in Diffusion Models
Python UpdatedSep 22, 2024 -
-
-
MOOD Public
Forked from SeulLee05/MOODOfficial code repository for the paper Exploring Chemical Space with Score-based Out-of-distribution Generation (ICML 2023)
Python MIT License UpdatedAug 9, 2024 -
AlignProp Public
Forked from mihirp1998/AlignPropAlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods…
Python MIT License UpdatedAug 2, 2024 -
SEIKO Public
SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all baselines (PPO, classifier-based guidance, direct reward ba…
-
ddpo-pytorch Public
Forked from kvablack/ddpo-pytorchDDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
Python MIT License UpdatedMay 17, 2024 -
cos598d_pruning Public
Forked from ruipeterpan/cos598d_pruningAssignments for COS598D: System and Machine Learning
Jupyter Notebook UpdatedApr 22, 2024 -
-
GDPO Public
Forked from sail-sg/GDPOGraph Diffusion Policy Optimization
Python UpdatedApr 11, 2024 -
-
DiGress Public
Forked from cvignac/DiGresscode for the paper "DiGress: Discrete Denoising diffusion for graph generation"
Python MIT License UpdatedNov 22, 2023 -
ddpo-jax Public
Forked from jannerm/ddpoCode for the paper "Training Diffusion Models with Reinforcement Learning"
Python MIT License UpdatedJul 5, 2023 -
-
-