Accepted Papers


AgriPerceiver: A Parameter-Efficient Vision-Language Model for Structured Macroscopic Crop Phenotyping
[Paper Link] [Poster Session 1]
AMR-Bench-mini: A Diagnostic Benchmark for Agentic Mechanistic AMR Reasoning under Evidence Insufficiency
[Paper Link] [Poster Session 1]
ARO: Aligned Representation learning for multi-Omics data
[Paper Link] [Poster Session 1]
Auditing a Multi-Modal Chromatin Foundation Model with Sparse Autoencoders
[Paper Link] [Poster Session 1]
Auditing Generative Graph Foundation Models for Connectomics: A Score × Predictor × Sampler Decomposition on Real Sparse Directed Connectomes
[Paper Link] [Poster Session 1]
Beyond Nativeness: Viral Proteins in Protein Language Models
[Paper Link] [Poster Session 2]
Biophysics-Guided Genomic Foundation Models via Attention Gating
[Paper Link] [Poster Session 1]
Bolek: A Multimodal Language Model for Molecular Reasoning
[Paper Link] [Poster Session 2]
Causal-IQD-DTA: Counterfactual Interaction-Quality Disentanglement for Robust Drug–Target Affinity Prediction
[Paper Link] [Poster Session 2]
Cell Painting Generates Single-Cell Transcriptomics via Conditional Diffusion
[Paper Link] [Poster Session 1]
ConfPert: Distribution-Free Conformal Coverage for Single-Cell Perturbation Predictors
[Paper Link] [Poster Session 1]
Contrastive Learning for Gene Set Enrichment Analysis Post-Processing
[Paper Link] [Poster Session 1]
Cross-modal transfer learning for mapping bulk transcriptomes at cellular level
[Paper Link] [Poster Session 2]
DELBERT-2: Pretrained Fingerprint Language Models for DEL Protein Binder Prediction
[Paper Link] [Poster Session 2]
Detecting Sparse Colorectal Cancer Signals from Multi-Modal Cell-Free DNA Representations Using Modern Hopfield Attention
[Paper Link] [Poster Session 1]
Do Clinical VLMs Need Dense Visual Tokens? Probing Spatial Grounding in Radiology Report Generation
[Paper Link] [Poster Session 2]
DrugAgent: Reliable Multi-Agent Aggregation under Conflicting Biomedical Evidence
[Paper Link] [Poster Session 2]
E1: Retrieval-Augmented Protein Encoder Models
[Paper Link] [Poster Session 2]
Empirical Observations on Parameter Scaling in Chemical Language Models
[Paper Link] [Poster Session 1]
ERVNet: A Three-Module Framework for Predicting Endogenous Retrovirus Reactivation, Gene Propagation, and Immunogenicity
[Paper Link] [Poster Session 1]
esm-bind: How much protein–RNA binding signal is already in frozen ESM-2 + RNA-FM representations?
[Paper Link] [Poster Session 1]
Exploring Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
[Paper Link] [Poster Session 1]
Few-Shot Biomedical Image Classification by Alignment of Independently Pretrained Encoders
[Paper Link] [Poster Session 2]
Gene-Embedding Perturbation Operators for Zero-Shot and Transferable Prediction of Transcriptional Responses
[Paper Link] [Poster Session 1]
Generalization of Protein Foundation Models for Engineered Fluorescent Biosensors
[Paper Link] [Poster Session 1]
GeneZip: Region-Aware Compression for Long Context DNA Modeling
[Paper Link] [Poster Session 2]
GFETM: Genome Foundation-based Embedded Topic Model for scATAC-seq Modeling
[Paper Link] [Poster Session 1]
Group Contrastive Learning for Weakly Paired Multimodal Data
[Paper Link] [Poster Session 2]
HealthBot: An Open-Source AI Assistant for Longitudinal Personal Health Management
[Paper Link] [Poster Session 2]
HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning
[Paper Link] [Poster Session 1]
How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images
[Paper Link] [Poster Session 1]
ImmunoFoundation: A Multimodal Foundation Model for Immunogenicity Prediction and Peptide Optimization
[Paper Link] [Poster Session 1]
Is PEFT Enough for Cell Segmentation? An Empirical No-Go Result on Frozen Foundation Models
[Paper Link] [Poster Session 1]
Learning Protein Fitness Landscapes with Multimodal Stability Priors
[Paper Link] [Poster Session 2]
Lightweight Alignment of Unimodal Foundation Models for Metabolite Identification
[Paper Link] [Poster Session 2]
LLMs Can Learn the Language of the Microbiome
[Paper Link] [Poster Session 2]
Local-Atlas Control-Anchored Flow Matching for Unpaired Single-Cell Perturbation Prediction
[Paper Link] [Poster Session 2]
Marking the Wrong Symptoms: Evaluating LLM Watermarks in Medical Texts
[Paper Link] [Poster Session 1]
Mechanistic Synergy in Multi-Modal VEP: DNA Context Complements PLMs under Biophysical Constraints
[Paper Link] [Poster Session 1]
Medmarks: An Open-Source LLM Benchmark Suite for Medical Tasks
[Paper Link] [Poster Session 1]
MESH-HR: Multimodal Fusion of Somatic DNA Profiles and Histopathology for Continuous Breast Cancer Receptor Subtyping via LLM-Assisted Annotation
[Paper Link] [Poster Session 2]
Mode-Aware Phenotype Profiling from Korean Clinical Reports: An LLM-Derived Two-Layer Fingerprint for Autism Characterization
[Paper Link] [Poster Session 2]
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
[Paper Link] [Poster Session 2]
Neuro-Anatomy–Informed Self-Supervised Learning for Structural Brain MRI
[Paper Link] [Poster Session 2]
OmicsDefense: The First Unified Framework for Defending Against Backdoor Attacks in Single-cell Foundation Models
[Paper Link] [Poster Session 1]
OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning
[Paper Link] [Poster Session 1]
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
[Paper Link] [Poster Session 2]
PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining
[Paper Link] [Poster Session 1]
PertReasonQA: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
[Paper Link] [Poster Session 1]
PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
[Paper Link] [Poster Session 2]
Position: AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes
[Paper Link] [Poster Session 1]
Position: Multi-Modal LLMs for Video Behavioral Coding in High-Stakes Decision-Making Are Bounded by Polysemy, Not by Model Scale
[Paper Link] [Poster Session 2]
Position: Multi-Omics Foundation Models Need a Modality Identifiability Standard, Not Just Aggregate Accuracy
[Paper Link] [Poster Session 1]
Position: Saturation in Single-Cell Foundation Model Benchmarks Signals Identifiability Failure, Not Solved Capability
[Paper Link] [Poster Session 2]
Position: Saturation in Single-Cell Foundation Model Benchmarks Signals Identifiability Failure, Not Solved Capability
[Paper Link] [Poster Session 2]
Pre-training on noncovalent interactions from synthetic protein-ligand structures to better predict binding affinity
[Paper Link] [Poster Session 1]
Predicting host-pathogen interactions using a proteome-scale language model
[Paper Link] [Poster Session 1]
PRIMA: a bidirectional state-space architecture and training approach for sequence modelling of protein-protein interactions
[Paper Link] [Poster Session 2]
Probing, Fusion, and Trustworthiness: A Systematic Evaluation of Foundation Model Representations for Multimodal Cancer Analysis
[Paper Link] [Poster Session 2]
ProSAM: Modular and Energy-Guided Fine-Tuning of Protein Language Models for Structure Prediction
[Paper Link] [Poster Session 2]
ProteinJEPA: Latent prediction complements protein language models
[Paper Link] [Poster Session 2]
ProteomeLM: A Proteome-Scale Language Model Enables Accurate and Rapid Prediction of Protein-Protein Interactions and Gene Essentiality Across Taxa
[Paper Link] [Poster Session 1]
PROTEUS: Predicting How Post-Translational Modifications Alter Drug Binding Affinity
[Paper Link] [Poster Session 2]
ProtQueSt: Query-Conditioned Retrieval-Augmented Generation for Protein Function Annotation
[Paper Link] [Poster Session 2]
ProtSent: Protein Sentence Transformers
[Paper Link] [Poster Session 1]
Retrieval-Augmented Foundation Model Enhances Risk Prediction Using Electronic Health Records
[Paper Link] [Poster Session 2]
SaNano - Structure Aware Transfer Learning For Data Limited Protein Modality
[Paper Link] [Poster Session 1]
Search, Edit, and Fold: LLM-Guided MSA Optimization for Protein Conformation Prediction
[Paper Link] [Poster Session 1]
Selective Benefits of Sequence-Drug Multimodal Learning for Antimicrobial Resistance Prediction
[Paper Link] [Poster Session 1]
SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
[Paper Link] [Poster Session 2]
Single-Cell Cross-Modal Transfer by Adversarial Fine-Tuning of Foundation Models
[Paper Link] [Poster Session 2]
Structural Bottleneck Reasoning: Efficient Medical VQA via Concept Alignment
[Paper Link] [Poster Session 2]
Survival-Relevant Directional Pathology–Omics Discordance from Frozen Whole-Slide Foundation Embeddings
[Paper Link] [Poster Session 1]
Synergy-Aware Contrastive Pretraining for Co-recorded Physiological Signals
[Paper Link] [Poster Session 1]
The Hallucination Dependence Index: A Cross-Condition Diagnostic for Clinical-LLM Faithfulness
[Paper Link] [Poster Session 2]
Transcriptomics-Conditioned Virtual Tissue Synthesis via Diffusion Transformers
[Paper Link] [Poster Session 2]
Transferable Lesion-Supervised Speech Representations for Post-Stroke Modelling
[Paper Link] [Poster Session 1]
TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness Prediction
[Paper Link] [Poster Session 1]
Uncovering evolutionarily remote and highly potent antimicrobial peptides with protein language models
[Paper Link] [Poster Session 2]
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
[Paper Link] [Poster Session 2]
Virtual Cell Models Inflate Perturbation Effect Sizes and Undermine Causal Gene Regulatory Network Recovery
[Paper Link] [Poster Session 2]
VirtualCeLLM: A Comprehensive Benchmark and Guidance for Large Language Models in Cellular Biology
[Paper Link] [Poster Session 1]
WACA-DTA: Water-Aware Geometric Biases for Structure-Conditioned Drug-Target Affinity Prediction
[Paper Link] [Poster Session 2]
What Makes a Virtual Cell a World Model? Three Gaps, Three Axes, and a Roadmap
[Paper Link] [Poster Session 2]