ICML 2026 Past Large language modelsAI for scienceMultimodal
ICML 2026 3rd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences
ICML 2026 FM4LS Workshop
- Submission deadline
- May 11, 2026, 16:59 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 (83)
Fetched from OpenReview (v2) on 2026-06-10.
-
AgriPerceiver: A Parameter-Efficient Vision-Language Model for Structured Macroscopic Crop Phenotyping
-
AMR-Bench-mini: A Diagnostic Benchmark for Agentic Mechanistic AMR Reasoning under Evidence Insufficiency
-
ARO: Aligned Representation learning for multi-Omics data
-
Auditing Generative Graph Foundation Models for Connectomics: A Score × Predictor × Sampler Decomposition on Real Sparse Directed Connectomes
-
Beyond Nativeness: Viral Proteins in Protein Language Models
-
Biophysics-Guided Genomic Foundation Models via Attention Gating
-
Bolek: A Multimodal Language Model for Molecular Reasoning
-
Causal-IQD-DTA: Counterfactual Interaction-Quality Disentanglement for Robust Drug–Target Affinity Prediction
-
Cell Painting Generates Single-Cell Transcriptomics via Conditional Diffusion
-
ConfPert: Distribution-Free Conformal Coverage for Single-Cell Perturbation Predictors
-
Contrastive Learning for Gene Set Enrichment Analysis Post-Processing
-
Cross-modal transfer learning for mapping bulk transcriptomes at cellular level
-
DELBERT-2: Pretrained Fingerprint Language Models for DEL Protein Binder Prediction
-
Detecting Sparse Colorectal Cancer Signals from Multi-Modal Cell-Free DNA Representations Using Modern Hopfield Attention
-
Do Clinical VLMs Need Dense Visual Tokens? Probing Spatial Grounding in Radiology Report Generation
-
DrugAgent: Reliable Multi-Agent Aggregation under Conflicting Biomedical Evidence
-
E1: Retrieval-Augmented Protein Encoder Models
-
Empirical Observations on Parameter Scaling in Chemical Language Models
-
ERVNet: A Three-Module Framework for Predicting Endogenous Retrovirus Reactivation, Gene Propagation, and Immunogenicity
-
esm-bind: How much protein–RNA binding signal is already in frozen ESM-2 + RNA-FM representations?
-
Exploring Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
-
Few-Shot Biomedical Image Classification by Alignment of Independently Pretrained Encoders
-
Gene-Embedding Perturbation Operators for Zero-Shot and Transferable Prediction of Transcriptional Responses
-
Generalization of Protein Foundation Models for Engineered Fluorescent Biosensors
-
GeneZip: Region-Aware Compression for Long Context DNA Modeling
-
GFETM: Genome Foundation-based Embedded Topic Model for scATAC-seq Modeling
-
Group Contrastive Learning for Weakly Paired Multimodal Data
-
HealthBot: An Open-Source AI Assistant for Longitudinal Personal Health Management
-
HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning
-
How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
-
ImmunoFoundation: A Multimodal Foundation Model for Immunogenicity Prediction and Peptide Optimization
-
Is PEFT Enough for Cell Segmentation? An Empirical No-Go Result on Frozen Foundation Models
-
Learning Protein Fitness Landscapes with Multimodal Stability Priors
-
Lightweight Alignment of Unimodal Foundation Models for Metabolite Identification
-
LLMs Can Learn the Language of the Microbiome
-
Local-Atlas Control-Anchored Flow Matching for Unpaired Single-Cell Perturbation Prediction
-
Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts
-
Mechanistic Synergy in Multi-Modal VEP: DNA Context Complements PLMs under Biophysical Constraints
-
Medmarks: An Open-Source LLM Benchmark Suite for Medical Tasks
-
MESH-HR: Multimodal Fusion of Somatic DNA Profiles and Histopathology for Continuous Breast Cancer Receptor Subtyping via LLM-Assisted Annotation
-
Mode-Aware Phenotype Profiling from Korean Clinical Reports: An LLM-Derived Two-Layer Fingerprint for Autism Characterization
-
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
-
Neuro-Anatomy–Informed Self-Supervised Learning for Structural Brain MRI
-
OmicsDefense: The First Unified Framework for Defending Against Backdoor Attacks in Single-cell Foundation Models
-
OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
-
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
-
PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining
-
PertReasonQA: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
-
PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
-
Position: AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes
-
Position: Multi-Modal LLMs for Video Behavioral Coding in High-Stakes Decision-Making Are Bounded by Polysemy, Not by Model Scale
-
Position: Multi-Omics Foundation Models Need a Modality Identifiability Standard, Not Just Aggregate Accuracy
-
Position: Saturation in Single-Cell Foundation Model Benchmarks Signals Identifiability Failure, Not Solved Capability
-
Position: Saturation in Single-Cell Foundation Model Benchmarks Signals Identifiability Failure, Not Solved Capability
-
Pre-training on noncovalent interactions from synthetic protein-ligand structures to better predict binding affinity
-
Predicting host-pathogen interactions using a proteome-scale language model
-
PRIMA: a bidirectional state-space architecture and training approach for sequence modelling of protein-protein interactions
-
Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis
-
ProSAM: Modular and Energy-Guided Fine-Tuning of Protein Language Models for Structure Prediction
-
ProteinJEPA: Latent prediction complements protein language models
-
ProteomeLM: A Proteome-Scale Language Model Enables Accurate and Rapid Prediction of Protein-Protein Interactions and Gene Essentiality Across Taxa
-
PROTEUS: Predicting How Post-Translational Modifications Alter Drug Binding Affinity
-
ProtQueSt: Query-Conditioned Retrieval-Augmented Generation for Protein Function Annotation
-
ProtSent: Protein Sentence Transformers
-
Retrieval-Augmented Foundation Model Enhances Risk Prediction Using Electronic Health Records
-
SaNano - Structure Aware Transfer Learning For Data Limited Protein Modality
-
Search, Edit, and Fold: LLM-Guided MSA Optimization for Protein Conformation Prediction
-
Selective Benefits of Sequence-Drug Multimodal Learning for Antimicrobial Resistance Prediction
-
SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
-
Single-Cell Cross-Modal Transfer by Adversarial Fine-Tuning of Foundation Models
-
Structural Bottleneck Reasoning: Efficient Medical VQA via Concept Alignment
-
Survival-Relevant Directional Pathology–Omics Discordance from Frozen Whole-Slide Foundation Embeddings
-
Synergy-Aware Contrastive Pretraining for Co-recorded Physiological Signals
-
The Hallucination Dependence Index: A Cross-Condition Diagnostic for Clinical-LLM Faithfulness
-
Transcriptomics-Conditioned Virtual Tissue Synthesis via Diffusion Transformers
-
Transferable Lesion-Supervised Speech Representations for Post-Stroke Modelling
-
TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction
-
Uncovering evolutionarily remote and highly potent antimicrobial peptides with protein language models
-
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
-
Virtual Cell Models Inflate Perturbation Effect Sizes and Undermine Causal Gene Regulatory Network Recovery
-
VirtualCeLLM: A Comprehensive Benchmark and Guidance for Large Language Models in Cellular Biology
-
WACA-DTA: Water-Aware Geometric Biases for Structure-Conditioned Drug-Target Affinity Prediction
-
What Makes a Virtual Cell a World Model? Three Gaps, Three Axes, and a Roadmap