iiinova — where your digital self keeps evolving

Reposted by Gonzalo Benegas

Open Athena @openathena.ai · 02/09/2026

With the generous support of The Jen-Hsun and Lori Huang Foundation, we have launched the largest live-streamed pretraining run in history, and Marin’s largest model yet: a fully open source 535B total parameter MoE model, with 18T tokens of data. Learn more at: openathena.ai/blog/huang-f...

openathena.ai

Marin's 535 billion parameter model training run launched with support of The Jen-Hsun and Lori Huang Foundation GPU gift

Open Athena announces the launch of Marin's largest training run yet—a 535B parameter large language model—with a generous gift of compute from The Jen-Hsun and Lori Huang Foundation.

0135

Gonzalo Benegas @gonzalobenegas.bsky.social · 06/08/2026

Excited to share MarinDNA, a 1B gLM that rivals Evo 2 40B on variant effect prediction while being 2,330x faster. With @eczech0.bsky.social, we built around a standard Transformer so we could reuse LLM infra and methods while focusing on data curation and scaling. openathena.ai/blog/marin-d... 🧵

1125

Reposted by Gonzalo Benegas

Al Merose @al.merose.com · 30/07/2026

Here's the tale of how @jder.bsky.social and I scaled Samudra, a neural ocean emulator capable of predicting 8 years of the ocean on a single GPU, to operate at a full 1/4° resolution (16x the size in bytes). It was quite a humbling process.

1183

Reposted by Gonzalo Benegas

Joana L. Rocha @joanocha.bsky.social · 08/06/2026

We are excited to share our pan-pangenome paper! This is a long time coming work of my postdoc with the incredible @psudmant.bsky.social, and a stellar group of people! I hope you enjoy reading it! And I am excited to talk more more about it this week at #PEQG26!! www.biorxiv.org/content/10.6...

biorxiv.org

A Pan-pangenome illuminates complex structural variation and selection in humans, chimpanzees, and bonobos

Complete, haplotype-resolved genome assemblies have provided unprecedented insight into the evolution of structurally complex, rapidly evolving regions of human genomes; however, population-scale pang...

15825

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 22/09/2025

We are excited to share GPN-Star, a cost-effective, biologically grounded genomic language modeling framework that achieves state-of-the-art performance across a wide range of variant effect prediction tasks relevant to human genetics. www.biorxiv.org/content/10.1... (1/n)

417690

Reposted by Gonzalo Benegas

Joana L. Rocha @joanocha.bsky.social · 25/06/2025

I am thrilled to announce that in January 2026 I will be starting my own lab at NYU Biology! Soon enough I will be recruiting postdocs and students! Please reach out if you are interested with a CV and description of your research interests, or if you know of people who could be interested! 🧬🗽 🦊

78318

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 23/05/2025

How can one efficiently simulate phylodynamics for populations with billions of individuals, as is typical in many applications, e.g., viral evolution and cancer genomics? In this work with M. Celentano, @wsdewitt.github.io , & S. Prillo, we provide a solution. doi.org/10.1073/pnas... 1/n

13715

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 07/04/2025

Thrilled to see my digital art on the cover of Trends Genet. The two binary strings represent reverse-complementary DNA sequences (00=A, 01=C, 10=G, 11=T) and the connecting rectangles represent “embeddings” learned by DNA language models. Pls check out our article as well: doi.org/10.1016/j.ti...

06913

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 04/03/2025

In our updated TraitGym preprint (w/ @gonzalobenegas.bsky.social & Gökcen Eraslan), we evaluate Evo 2 on regulatory variants associated with human traits. We see marked performance gains with scale on Mendelian traits, although still a bit behind alignment-based methods. doi.org/10.1101/2025... 1/n

13213

Gonzalo Benegas @gonzalobenegas.bsky.social · 13/02/2025

Can DNA sequence models predict mutations affecting human traits? We introduce TraitGym, a curated benchmark of causal regulatory variants for 113 Mendelian & 83 complex traits, and evaluate functional genomics and DNA language models. Joint work w/ Gökcen Eraslan and @yun-s-song.bsky.social 🧵👇

12815

Reposted by Gonzalo Benegas

bioRxiv Genetics @biorxiv-genetic.bsky.social · 13/02/2025

Benchmarking DNA Sequence Models for Causal Regulatory Variant Prediction in Human Genetics www.biorxiv.org/content/10.1101/202…

081

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 08/01/2025

Our work, which shows statistical issues with the previous claim of a severe ancient bottleneck in the ancestry of African populations, has been selected as a Featured article in Genetics. doi.org/10.1093/gene...

doi.org

A previously reported bottleneck in human ancestry 900 kya is likely a statistical artifact

Hu et al. (Science, 2023) recently inferred a severe ancient bottleneck around 900 thousand years (kya) ago in African ancestry but found no similar eviden

0154

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 03/01/2025

Coincidentally, another article from my lab on DNA language models got published on the same day as GPN-MSA. It's freely available for 50 days from this link: authors.elsevier.com/a/1kNCscQbJB... Genomic language models: opportunities and challenges Please share with your colleagues.

authors.elsevier.com

1102

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 02/01/2025

Happy New Year! Our GPN-MSA paper is finally published, under a slightly different title from the preprint. Please check it out and share it with your colleagues: doi.org/10.1038/s415... 1/4

doi.org

A DNA language model based on multispecies alignment predicts the effects of genome-wide variants - Nature Biotechnology

A language model predicts the effects of genetic variants in the human genome.

1167

Reposted by Gonzalo Benegas

Yun S. Song @yun-s-song.bsky.social · 16/11/2024

Large protein language models can learn complex epistatic interactions, but how much does that help with predicting variant effects? In this NeurIPS article, we show that classical independent-sites phylogenetic models can outperform pLMs on this task. 1/7 openreview.net/forum?id=H7m...

openreview.net

Ultrafast classical phylogenetic method beats large protein...

Amino acid substitution rate matrices are fundamental to statistical phylogenetics and evolutionary biology. Estimating them typically requires reconstructed trees for massive amounts of aligned...

29044