zhaoyl18 / SEIKOLinks
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.
☆22Updated 10 months ago
Alternatives and similar repositories for SEIKO
Users that are interested in SEIKO are comparing it to the libraries listed below
Sorting:
- Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences li…☆138Updated 8 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆30Updated last year
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆18Updated 3 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆31Updated 8 months ago
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆51Updated 3 weeks ago
- Inference-Time Alignment in Protein Diffusion Models☆36Updated 4 months ago
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆55Updated last month
- ☆17Updated 2 years ago
- Code for our paper "Unlocking Guidance for Discrete State-Space Diffusion and Flow Models"☆19Updated last month
- Code repository for Trajectory Flow Matching☆66Updated 7 months ago
- Code for the paper https://arxiv.org/abs/2402.04997☆78Updated last year
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆69Updated last year
- ☆24Updated last year
- ☆32Updated 11 months ago
- Benchmarks for Model-Based Optimization☆92Updated last year
- Derivative-Free, Training-Free, Guidance in Diffusion Models☆13Updated 8 months ago
- [NeurIPS 2023] Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement☆14Updated 7 months ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆93Updated 3 months ago
- Baselines for Model-Based Optimization installation fixes and compatible with newer AMPERE+ GPUs (e.g. 3090)☆11Updated 2 years ago
- Official implementation of ICML'24 paper "Offline Multi-Objective Optimization".☆20Updated this week
- Learning energy decompositions for partial inference in GFlowNets☆16Updated last year
- Simple Guidance Mechanisms for Discrete Diffusion Models☆39Updated 5 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆61Updated last month
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆23Updated 2 months ago
- This repository is the official implementation of Bidirectional Learning for Offline Infinite-width Model-based Optimization (NeurIPS 202…☆15Updated 2 years ago
- ☆34Updated 2 months ago
- ☆16Updated last year
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆22Updated 2 weeks ago
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control☆36Updated last week
- QGFN: Controllable Greediness with Action Values - Code☆10Updated last year