arXiv Machine Learning June 18, 2026 By Yanjun Shao, Yundi Chen, Yashvi Patel, Aurelien Pelissier, Mar\'ia Rodr\'iguez Mart\'inez

Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

Read the original on arXiv Machine Learning →

arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 4

SIGMA: Semantic Identifier Grouping for Molecular Autoregression

arXiv:2603. 25062v2 Announce Type: replace Abstract: Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization.

By Xinyu Wang, Fei Dou, Jinbo Bi, Minghu Song

benchmarks safety

Hugging Face Trending Papers

Jul 6

Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations

Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles. Preclinical transfer-learning models can simulate drug-induced expression changes but are often hard to interpret and unstable, whereas knowledge-graph methods provide mechanistic context yet remain static and fail to capture drug-induced transcriptomic perturbation dynamics.

rag diffusion benchmarks

arXiv AI

Jun 2

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

arXiv:2606. 01042v1 Announce Type: cross Abstract: Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions.

By Xinyu Yuan, Xixian Liu, Jianan Zhao, Yashi Zhang, Hongyu Guo, Jian Tang

llms

arXiv AI

Jul 7

Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations

arXiv:2607. 04557v1 Announce Type: cross Abstract: Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles.

By Dongmin Bang, Sugyun An, Inyoung Sung, Ilho Yun, Sun Kim, Sangseon Lee

rag diffusion benchmarks

arXiv Machine Learning

Jun 26

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.

By John Sweeney

llms rag nlp safety

arXiv AI

Aug 12

JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures

arXiv:2602. 17162v3 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature".

By Ariel Larey, Elay Dahan, Amit Bleiweiss, Raizy Kellerman, Guy Leib, Omri Nayshool, Dan Ofer, Tal Zinger, Dan Dominissini, Gideon Rechavi, Nicole Bussola, Simon Lee, Shane O'Connell, Dung Hoang, Marissa Wirth, Alexander W. Charney, Nati Daniel, Yoli Shavit

rag diffusion benchmarks safety

Related stories

SIGMA: Semantic Identifier Grouping for Molecular Autoregression

Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

JEPA-DNA: Grounding Genomic Foundation Models through Joint-Embedding Predictive Architectures