# Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes

arXiv: https://arxiv.org/abs/2610.19053 · HTML: https://mlsanity.com/paper/2610.19053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 96 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer](https://mlsanity.com/paper/2203.03466/) (2022)
- [Real-time gravitational-wave science with neural posterior estimation](https://mlsanity.com/paper/2106.12594/) (2021)
- [Edit Flows: Flow Matching with Edit Operations](https://mlsanity.com/paper/2506.09018/) (2025)
- [DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra](https://mlsanity.com/paper/2502.09571/) (2025)
- [PhyloGFN: Phylogenetic inference with generative flow networks](https://mlsanity.com/paper/2310.08774/) (2023)
- [Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion](https://mlsanity.com/paper/2506.08316/) (2025)
- [Learnable Topological Features for Phylogenetic Inference via Graph Neural Networks](https://mlsanity.com/paper/2302.08840/) (2023)
- [Unlocking Point Processes through Point Set Diffusion](https://mlsanity.com/paper/2410.22493/) (2024)
- [Variational Combinatorial Sequential Monte Carlo Methods for Bayesian Phylogenetic Inference](https://mlsanity.com/paper/2106.00075/) (2021)
- [GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies](https://mlsanity.com/paper/2307.03675/) (2023)
- [A Variational Approach to Bayesian Phylogenetic Inference](https://mlsanity.com/paper/2204.07747/) (2022)
- [A Diffusion Model to Shrink Proteins While Maintaining Their Function](https://mlsanity.com/paper/2511.07390/) (2025)
- [SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups](https://mlsanity.com/paper/2410.02942/) (2024)
- [ARTree: A Deep Autoregressive Model for Phylogenetic Inference](https://mlsanity.com/paper/2310.09553/) (2023)
- [Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space](https://mlsanity.com/paper/2501.17965/) (2025)
- [PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation](https://mlsanity.com/paper/2412.18827/) (2024)
- [PhyloVAE: Unsupervised Learning of Phylogenetic Trees via Variational Autoencoders](https://mlsanity.com/paper/2502.04730/) (2025)
- [Brownian motion, bridges and Bayesian inference in phylogenetic tree space](https://mlsanity.com/paper/2506.22135/) (2025)

## Abstract (arXiv)

Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking pathogen spread to reconstructing the history of life. Conventionally, practitioners obtain posteriors over trees using likelihood-based methods like MCMC. However, likelihoods are only available for simple evolutionary models with restrictive assumptions. For realistic evolutionary models, inference using conventional methods is prohibitively expensive, inaccurate, or even impossible. In practice, practitioners settle for using as flexible a conventional method as possible, even though they expect it is misspecified. In principle, we could use simulation-based inference: simulate tree and sequence data from an evolutionary model and train a neural network to predict the posterior over trees given sequences. However it is a mathematical challenge to represent and train complex posterior distributions over trees. Here we present a flexible family of conditional generative models over trees. Our models iteratively build trees using three natural paradigms -- top-down, middle-out, or bottom-up -- and are trained using a discrete diffusion framework. For real and synthetic datasets of up to 65 taxa and >105 tokens, our models recover MCMC posteriors much more accurately than the previous state-of-the-art simulation-based method Phyloformer 2. Finally, we compare to IQ-Tree, a popular flexible-but-misspecified conventional method. Our models match its tree estimates on simple data, but on more realistic data, our method is reliably more accurate.