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.
☆30Jul 18, 2024Updated last year
Alternatives and similar repositories for SEIKO
Users that are interested in SEIKO are comparing it to the libraries listed below
Sorting:
- [ICLR 2024 Spotlight] Code for the paper "Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making"☆12Apr 22, 2024Updated last year
- Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences li…☆157Sep 15, 2024Updated last year
- Subtask-Aware Visual Reward Learning from Segmented Demonstrations (ICLR 2025 accepted)☆18Apr 11, 2025Updated 10 months ago
- Official implementation for Diffusion Alignment as Sampling (DAS), ICLR'25, Spotlight☆59Feb 12, 2025Updated last year
- [ICML 24] Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space☆16Aug 9, 2024Updated last year
- Computational analysis of nucleic acids structures using graph neural networks☆15Mar 25, 2024Updated last year
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆64May 10, 2025Updated 9 months ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆40May 9, 2024Updated last year
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆314Nov 1, 2024Updated last year
- Generative models and other stuff too, maybe, perhaps even probably☆16Dec 12, 2015Updated 10 years ago
- Official code repository for the paper Exploring Chemical Space with Score-based Out-of-distribution Generation (ICML 2023)☆40May 19, 2024Updated last year
- The collection of my research papers' illustrations.☆19Oct 15, 2023Updated 2 years ago
- ☆23Oct 20, 2023Updated 2 years ago
- Tracking literature and additional online resources on transformers for sequential decision making including RL and beyond.☆49Dec 21, 2022Updated 3 years ago
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆24Feb 27, 2025Updated last year
- Official codebase for GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning.☆29Nov 12, 2024Updated last year
- Offline Reinforcement Learning Reading Group☆28Nov 22, 2022Updated 3 years ago
- ☆32Jul 10, 2023Updated 2 years ago
- An official 're'-implementation of Physics-induced graph neural network: An application to wind-farm power estimation (PGNN).☆29Jul 27, 2021Updated 4 years ago
- Official repository for GFACS☆33May 17, 2024Updated last year
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆554Jul 5, 2023Updated 2 years ago
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆746Mar 22, 2024Updated last year
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆35Nov 3, 2023Updated 2 years ago
- Implementation of PCA algorithm using Gram-Scmidt modification on NIPALS☆10Jun 13, 2015Updated 10 years ago
- NeurIPS24: Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization☆41Apr 2, 2025Updated 11 months ago
- ☆39Jul 2, 2023Updated 2 years ago
- Factoried Personalized Markov Chains for Next Basket Recommendation in R and Python☆13Jan 7, 2018Updated 8 years ago
- ☆10Nov 15, 2023Updated 2 years ago
- Contains implementation of the DoubIL and ResiduIL algorithms from the ICML '22 paper Causal Imitation Learning under Temporally Correlat…☆11Dec 9, 2022Updated 3 years ago
- Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation. In Recsys23.☆11Jul 18, 2023Updated 2 years ago
- ☆10Jul 8, 2021Updated 4 years ago
- dynamic planning, hybrid models, hierarchical active inference, tool use☆13Jun 13, 2025Updated 8 months ago
- Code for (MobiCom24) Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning☆13Dec 10, 2024Updated last year
- Run large scale tensor and coupled matrix-tensor factorization on top of stock Hadoop.☆18Dec 28, 2017Updated 8 years ago
- Safe Model-Based RL HVAC Control Using Epistemic Uncertainty Estimation.☆11Feb 25, 2025Updated last year
- Single-Life Reinforcement Learning☆14Dec 17, 2022Updated 3 years ago
- Benchmarks for Model-Based Optimization☆97Apr 21, 2024Updated last year
- Course Website for "AI618: Generative Model and Unsupervised Learning"☆37May 23, 2023Updated 2 years ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆214Jun 26, 2025Updated 8 months ago