Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025PLoS Computational BiologyOpen Access

ARTreeFormer: A faster attention-based autoregressive model for phylogenetic inference

View Full Paper
Ask AI
Bookmark
Share

Authors

TXTianyu Xie

Discussion

Loading...

Member takes

Overview

New autoregressive model improves computation speed and accuracy in phylogenetic inference, suggesting effectiveness for large datasets.

Key Points

  • To enhance the scalability of phylogenetic inference through the development of ARTreeFormer.
  • Introduced ARTreeFormer, leveraging fixed-point iteration and attention mechanisms.
  • Performed vectorized computation, particularly optimized for CUDA devices.
  • Compared model performance on various real data phylogenetic inference problems.
  • Demonstrated significant improvements in computation speed compared to previous methods.
  • Maintained high levels of approximation performance in phylogenetic inference challenges.

Cite This Study

Tianyu Xie (2025) studied this question.

synapsesocial.com/papers/693624dd4fa91c937236d1echttps://doi.org/10.1371/journal.pcbi.1013768
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Torchtree: flexible phylogenetic model development and inference using PyTorch2024
  2. 2A model-free method for genealogical inference without phasing and its application for topology weighting2025
  3. 3TaxaTreeMapper: A Novel Algorithm for Phylogenetic Ancestral State Reconstruction Using Set Theory2025
  4. 4A model-free method for genealogical inference without phasing and its application for topology weighting2025
  5. 5The Tree Reconstruction Game: Phylogenetic Reconstruction Using Reinforcement Learning2024 · 14 citations