ICML 2025 Past Large language modelsAI for scienceMultimodal
ICML 2025 Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences
FM4LS 2025
- Submission deadline
- May 27, 2025, 18:59 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (69)
Fetched from OpenReview (v2) on 2026-06-10.
-
3D-SBDD meets LLM: Towards FDA-Level Drug Design
-
A Foundation Model for Mass Spectrometry Proteomics
-
A Genomic Language Model for Zero-Shot Prediction of Promoter Indel Effects
-
A Look at the Isotropy of Pretrained Protein Language Models
-
A Multi-Modal Large Language Model for Free-Form, Open-Ended, and Interactive Prediction of Properties and Mechanisms of Candidate Drug Molecules
-
Advancing Knotted Protein Design with ESM3: Guided Generation and Topological Insights
-
AIDO.Tissue: Spatial Cell-Guided Pretraining for Scalable Spatial Transcriptomics Foundation Model
-
An Interventional Framework of Multimodal Epigenomic Regulation for Gene Expression Prediction
-
AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization
-
ATOMICA: Learning Universal Representations of Intermolecular Interactions
-
Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning
-
BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models
-
Cell-Type-Aware Pooling for Robust Sample Classification in Single-Cell RNA-seq Data
-
Challenges and Guidelines in Deep Generative Protein Design: Four Case Studies
-
Closing the gap between the biology and the clinic with a foundation model of immunology and inflammation
-
Conditional Normalizing Flows for the Design of T Cell Therapies
-
DeepSeq: High-Throughput Single-Cell RNA Sequencing Data Labeling via Web Search-Augmented Agentic Generative AI Foundation Models
-
Describe Anything in Medical Images
-
DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing
-
Enriched Instruction-Following Graph Alignment for Efficient Medical Vision-Language Models
-
Evaluating Multi-Modal Models for Enzyme-Reaction Retrieval
-
From Vision to Graph Self-Supervised Learning in Digital Pathology
-
GeneChat: A Multi-Modal Large Language Model for Gene Function Prediction
-
H&Enium, Applying Foundation Models to Computational Pathology and Spatial Transcriptomics to Learn an Aligned Latent Space
-
HPP-Voice: A Large-Scale Evaluation of Speech Embeddings for Multi-Phenotypic Classification
-
Ibex: Pan-immunoglobulin structure prediction
-
Integrating Pathology Foundation Models and Spatial Transcriptomics for Cellular Decomposition from Histology Images
-
Joint Diffusion Sampling via Positive-Unlabeled Guidance for Multi-Modal Data
-
KD-CPT: A Knowledge-Driven Cellular Phenotypic Transdifferentiation Model
-
Knowledge Graph-Augmented DNA Representation Learning
-
Learning Diffusion Models with Flexible Representation Guidance
-
Leveraging the Structure of Medical Data for Improved Representation Learning
-
Ligand Iterative Sampling for Affinity Refinement and Drug Discovery (LISARDD)
-
MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models
-
Molecularly informed analysis of histopathology images using natural language
-
Multi-Modal Interpretable Graph for Competing Risk Prediction with Electronic Health Records
-
Multi-Modal Large Language Model Enables Protein Function Prediction
-
Multi-Modal Medical Image Augmentation for Controlled Heterogeneity and Fair Outcomes
-
Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design
-
Multi-Objective-Guided Generative Design of mRNA with Therapeutic Properties
-
Multimillion cell self-supervised representation learning enables organ-scale tissue niche discovery
-
Multimodal Benchmarking of Foundation Model Representations for Cellular Perturbation Response Prediction
-
Multimodal Modeling of CRISPR-Cas12 Activity Using Foundation Models and Chromatin Accessibility Data
-
Multimodal Protein Language Models for Flexibility Prediction and Loop Design
-
NextGenPLM: A Novel Structure-Infused Foundational Protein Language Model for Antibody Discovery and Optimization
-
PM1: A Foundation Model Fusing Genotype, Phenotype, and Image for Precision Medicine
-
Promoter Sequence Generation using Homology Prompting
-
ProteinAligner: A Tri-Modal Contrastive Learning Framework for Protein Representation Learning
-
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
-
Rapid and Reproducible Multimodal Biological Foundation Model Development with AIDO.ModelGenerator
-
RepoLLM: A Multi-modal Foundation Model for Drug Repurposing via Alignment of Molecules, EHRs, and Knowledge Graphs
-
Retrieval Augmented Protein Language Models for Protein Structure Prediction
-
Robust Multi-Omics Integration from Incomplete Modalities Significantly Improves Prediction of Alzheimer’s Disease
-
Scaling up measurement noise scaling laws
-
Segmentation Helps Understanding: Mask-Infused Vision-Language Pre-training for 3D Medical Images
-
Self-Supervised Representation Learning for Microbiome Improves Downstream Prediction in Data-Limited Settings and Cross-Cohort Generalizability
-
SHIVER: Somatic Hypermutation Informed Vocabulary Encoder Representations
-
SOAPIA: Siamese-Guided Generation of Off Target-Avoiding Protein Interactions with High Target Affinity
-
Stabilizing protein fitness predictors via the PCS framework
-
Temporal Representation Learning for Ultrasound Analysis using Masked Modeling
-
TICA-Based Free Energy Matching for Machine-Learned Molecular Dynamics
-
Towards foundation models that learn across biological scales
-
Towards functional annotation with latent protein language model features
-
Towards Molecular Conformer Generation with Language Models
-
Transfer Learning of Condition-Specific Perturbation in Gene Interactions: Towards Multi-modal Foundational Modeling of Drug Response
-
Transferring Cell-level Drug Response to Patient via Tumor Heterogeneity-Aware Alignment and Gene-level Foundational Models
-
TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
-
Uncertainty-Aware Discrete Diffusion Improves Protein Design
-
Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning