ARGformer lands in Bioinformatics: turning genealogical topologies into language-style embeddings
anshulkundaje · x · 2026-09-04
ARGformer, published in Bioinformatics, learns haplotype-level genome representations directly from inferred ancestral recombination graphs (ARGs), analogous to how PCA extracts population structure from genotypes.
It converts local genealogical paths into tokens and learns dense embeddings similar to language embeddings, enabling visualization, clustering and querying. Code is open-sourced.
More from Research
- Martian says routing across 44 LLMs cuts errors 46% vs best single model on 16 benchmarks — Arindam_1729 · 2026-09-04
- Bengio co-authors arXiv framework for monitoring rogue AI progression, born from FFRDC cross-lab workshop — Miles_Brundage · 2026-09-04
- FlashRender: Few-step camera-controlled generative rendering via MeanFlow distillation — everex · 2026-09-04
- LatentStream: progressive latent memory evolution for streaming video understanding — Hongyu Qu · 2026-09-04
- Temporal Context Routing aligns script timing in joint audio-video generation — Yichen Liu · 2026-09-04
- Puffin-World scales unified multimodal model with native 3D world states — Kang Liao · 2026-09-04