reward-guidance
sanjitdp
Experiment code for 'Are we really tilting? The mechanics of reward guidance in flow and diffusion models' — plug-in Doob h-transform sampling, reward damping, best-of-n, and flow map reward guidance for Gaussian mixtures, a 2D checkerboard, and FLUX.1 text-to-image generation.
Growth over time
5 data points · 2026-07-21 → 2026-10-17How do you feel about this project?
Ask AI about reward-guidance
Question copied to clipboardWhat is the sanjitdp/reward-guidance GitHub project? Description: "Experiment code for 'Are we really tilting? The mechanics of reward guidance in flow and diffusion models' — plug-in Doob h-transform sampling, reward damping, best-of-n, and flow map reward guidance for Gaussian mixtures, a 2D checkerboard, and FLUX.1 text-to-image generation.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
🏆 Show off this rank
Add it to a GitHub README or profile — the card updates as the ranking changes:
How to clone reward-guidance
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the reward-guidance issue tracker:
Open GitHub Issues