Hence, during the training of VaiPhy, we used a maximum likelihood heuristic toupdate thebranch lengths givenatree topology. The branch lengths of the NJ tree are optimized with the same software. The optimized branch lengths are used as the initial set of lengths fore E(τ). In all of the figures, the left column is the current state ofτ, the middle column is two trees that are compared, and the right column is the selected tree. Solid lines indicate the edges inτ, and bold green lines are accepted edges (edges inM).

Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology). Traditional Markov Chain Monte Carlo methods face slow convergence and computational burdens. Existing Variational Inference methods, which require pre-generated topologies and typically treat tree structures and branch lengths independently, may overlook critical sequence features, limiting their accuracy and flexibility. We propose PhyloGen, a novel method leveraging a pre-trained genomic language model to generate and optimize phylogenetic trees without dependence on evolutionary models or aligned sequence constraints. PhyloGen views phylogenetic inference as a conditionally constrained tree structure generation problem, jointly optimizing tree topology and branch lengths through three core modules: (i) Feature Extraction, (ii) PhyloTree Construction, and (iii) PhyloTree Structure Modeling. Meanwhile, we introduce a Scoring Function to guide the model towards a more stable gradient descent. We demonstrate the effectiveness and robustness of PhyloGen on eight real-world benchmark datasets. Visualization results confirm PhyloGen provides deeper insights into phylogenetic relationships.

Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology).

We show that VBPI-NF significantly improves upon the vanilla VBPI on a benchmark of challenging real data Bayesian phylogenetic inference problems.

The update equations of V aiPhy follow the standard mean-field VI updates. Furthermore, i is the set of nodes except node i, and C is a constant. We utilize the NJ algorithm to initialize V aiPhy with a reasonable state. An example script to run PhyML is shown below. Here we provide two algorithmic descriptions of SLANTIS.