| # [AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance]() |
|
|
| **Tong Chen**, **Yinuo Zhang**, **Pranam Chatterjee** |
|
|
|  |
|
|
| Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single-objective guidance, while discrete approaches lack guarantees for multi-objective Pareto optimality. We introduce **AReUReDi** (**A**nnealed **Re**ctified **U**pdates for **Re**fining **Di**screte Flows), a discrete optimization algorithm with theoretical guarantees of convergence to the Pareto front. Building on Rectified Discrete Flows (ReDi), AReUReDi combines Tchebycheff scalarization, locally balanced proposals, and annealed Metropolis-Hastings updates to bias sampling toward Pareto-optimal states while preserving distributional invariance. Applied to peptide and SMILES sequence design, AReUReDi simultaneously optimizes up to five therapeutic properties (including affinity, solubility, hemolysis, half-life, and non-fouling) and outperforms both evolutionary and diffusion-based baselines. These results establish AReUReDi as a powerful, sequence-based framework for multi-property biomolecule generation. |
|
|
|
|
| Check out our paper on the [arXiv](https://arxiv.org/abs/2510.00352)! |
|
|
| ## Citation |
|
|
| If you find this repository helpful for your papers and research, please consider citing our paper: |
|
|
| ```python |
| @article{chen2025areuredi, |
| title={AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance}, |
| author={Tong Chen and Yinuo Zhang and Pranam Chatterjee}, |
| journal={arXiv preprint arXiv:2510.00352}, |
| year={2025} |
| } |
| ``` |
