arXiv:2604. 04287v2 Announce Type: replace Abstract: Foundation models in genomics have shown mixed success compared to their counterparts in natural language processing.
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".
The paper investigates why token prediction, a common pre‑training objective for language models, yields useful representations. It introduces a statistical framework linking token prediction accuracy to the geometry of token embeddings, showing that accurate predictions organize embeddings according to Hellinger distances between context distributions. The authors also propose a self‑consistency principle that refines contextual representations through repeated application of a shared block, and provide downstream guarantees for token generation, community recovery, and linear classification.
VANDAM is a framework that augments Genomic Foundation Models by incorporating DNA molecular priors into self‑supervised training. It predicts regional molecular properties from pooled representations and, when functional labels are available, injects local features at the input. The approach consistently improves downstream performance across multiple architecture families and genomic tasks, and probing experiments show that the priors generalize to unseen molecular properties.
arXiv:2608. 12090v1 Announce Type: new Abstract: Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology.
arXiv:2608.23551v1 Announce Type: cross Abstract: Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existi...
Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs).
arXiv:2605.07938v2 Announce Type: replace Abstract: Single-cell representation learning (SCRL) from gene expression data offers a way to uncover the complex regulatory logic underlying cellular funct...
arXiv:2509.20702v3 Announce Type: replace-cross Abstract: Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to...
arXiv:2608.30315v1 Announce Type: new Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...
arXiv:2607. 04733v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities.
arXiv:2607. 08803v1 Announce Type: cross Abstract: The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology.
CellMSA introduces a novel single‑cell representation learning framework that leverages a multiple‑sequence‑alignment‑inspired context model. For each target cell, it retrieves relevant cells across batches and related cell types, summarizing cross‑cell patterns into a context‑dependent gene‑pair representation that is fed into a pair‑aware encoder. Pretraining on a massive human single‑cell corpus (≈109 million cells) and subsequent benchmarks demonstrate consistent performance gains over existing methods.