Language Breakdown
Lines of code distribution across 10 owned repositories
T-Shaped Developer
T-shapedDeep in Jupyter Notebook with broad versatility
Collaboration Network
Global Impact visualization
Repos
25
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Top Repositories
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 backpropagation) for fine-tuning Stable Diffusion.
policy gradient methods for von Neumann's ratio game
Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (+ images)
Derivative-Free, Training-Free, Guidance in Diffusion Models
Open Source Impact
Contributions to external projects
No external contributions found.