ICML 2025 Past Generative models
ICML 2025 Generative AI and Biology (GenBio) Workshop
GenBio 2025
- Submission deadline
- May 26, 2025, 11:59 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 (145)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Diffusion Model to Shrink Proteins While Maintaining their Function
-
A Diffusion-Based Autoencoder for Learning Patient-Level Representations from Single-Cell Data
-
A framework to extract and interpret biological concepts from scRNAseq generative foundation models
-
A Genomic Language Model for Zero-Shot Prediction of Promoter Indel Effects
-
A Ground-Up Designed Controllable GPT for Molecule Optimization
-
A Zero-shot LLM-based Framework for Descriptive Gene-gene Interaction Network Generation
-
AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
-
Active Leaning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation
-
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
-
Amortized Sampling with Transferable Normalizing Flows
-
An Improved Systematic Method for Constructing Enzyme-Constrained Genome-Scale Metabolic Models Using a Protein-Chemical Transformer
-
An Iterative Framework for Generative Backmapping of Coarse Grained Proteins
-
Analytic Gaussian Convolution for Faster Molecular Optimization and Sampling
-
AntiDIF: Accurate and Diverse Antibody Specific Inverse Folding with Discrete Diffusion
-
AtoMAE: Learning Protein Structure Representations from Atomic Voxel Grids via Masked Autoencoders
-
ATOMICA: Learning Universal Representations of Molecular Interactions
-
Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models
-
Balancing Speed and Precision in Protein Folding: A Comparison of AlphaFold2, ESMFold, and OmegaFold
-
BC-Design: A Biochemistry-Aware Framework for Highly Accurate Inverse Protein Folding
-
Benchmark of Diffusion and Flow Matching Models for Unconditional Protein Structure Design
-
Beyond Visual Inspection: Principled Benchmarking of Single-Cell Trajectory Representations with scTRAM
-
Bimodal masked language modeling for bulk RNA-seq and DNA methylation representation learning
-
BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Design
-
Biological Reasoning with Reinforcement Learning through Natural Language Enables Generalizable Zero-Shot Cell Type Annotations
-
BoltzNCE: Learning Likelihoods for Boltzmann Generation with Stochastic Interpolants and Noise Contrastive Estimation
-
Bridging Quantum and Classical Computing in Drug Design: Architecture Principles for Improved Molecule Generation
-
Bures-Wasserstein Flow Matching for Graph Generation
-
Calibrating Generative Models
-
Chemical Reaction Network Implementation of Logic Gates and Neural Networks Using a Molecular Exchange Mechanism
-
CoFM: Molecular Conformation Generation via Flow Matching in SE(3)-Invariant Latent Space
-
Connecting Gene Expression and Tissue Morphology with Conditional Generative Models
-
Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models
-
Constrained Molecular Generation via Sequential Flow Model Fine-Tuning
-
CryoSAMU: Enhancing 3D Cryo-EM Density Maps of Protein Structures at Intermediate Resolution with Structure-Aware Multimodal U-Nets
-
DePO: Elicit Chemical Reasoning Capability via Demonstration-Guided Policy Optimization
-
Design in Voxel Space Decode in SMILES Space: Plixer Generates Drug-Like Molecules for Protein Pockets
-
Diffusion models with group symmetries for biomolecule generation
-
Diffusion-Free Graph Generation with Next-Scale Prediction
-
DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing
-
DIVER-0 : A Fully Channel Equivariant EEG Foundation Model
-
Diversity by Design: Addressing Mode Collapse Improves scRNA-seq Perturbation Modeling on Well-Calibrated Metrics
-
Do we need equivariant models for molecule generation?
-
Drug Discovery SMILES-to-Pharmacokinetics Diffusion Models with Deep Molecular Understanding
-
eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis
-
Efficient Models For Molecular Property Prediction
-
Electrostatics from Laplacian Eigenbasis for Neural Network Interatomic Potentials
-
Enhancing AlphaFold3 for Protein-Ligand Co-Folding via Reinforcement Learning
-
EpiBinder: a multimodal deep learning model at base-resolution to analyze in vivo Transcription Factor-DNA Binding
-
EpitopeGen: Learning to Generate T Cell Epitopes: A Semi-Supervised Approach with Biological Constraints
-
Exploring Adversarial Robustness in Classification tasks using DNA Language Models
-
Fast and Scalable Gene Embedding Search: A Comparative Study of FAISS and ScaNN
-
FIGRDock: Fast Interaction-Guided Regression for Flexible Docking
-
Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
-
Forecasting H1N1 Influenza Pandemic and Seasonal Evolution
-
Foreground-aware Virtual Staining for Accurate 3D Cell Morphological Profiling
-
FORT: Forward-Only Regression Training of Normalizing Flows
-
From Fragments to Geometry: A Unified Graph Transformer for Molecular Representation from Conformer Ensembles
-
Generating readily synthesizable dye scaffolds with SyntheFluor
-
Generation of structure-guided pMHC-I libraries using Diffusion Models
-
Guided Generation for Developable Antibodies
-
HM-GIM: A Probabilistic Neural Model for Discovering Heterogeneous Microbiome or Human Gene Groupings and Their Interactions
-
How Good is AlphaFold3 at Ranking Drug Binding Affinities?
-
HybridLinker: Topology-Guided Posterior Sampling for Enhanced Diversity and Validity in 3D Molecular Linker Generation
-
Ibex: Pan-immunoglobulin structure prediction
-
Importance-Weighted Training of Diffusion Samplers
-
Improving Genomic Models via Task-Specific Self-Pretraining
-
Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
-
In silico design of epigenetic reprogramming payloads
-
Integrating Bilinear Transduction with Message Passing Neural Networks for Improved ADMET Property Prediction
-
Intrinsic Evaluation of DNA Embeddings in Genome Language Models: Insights from Yeast Genomic Sequences
-
JAMUN: Bridging Smoothed Molecular Dynamics and Score-Based Learning for Conformational Ensemble Generation
-
Joint Probabilistic Modeling of Pseudobulk and Single-Cell Transcriptomics Enables Accurate Estimation of Cell Type Composition
-
KODA: An agentic framework for KEGG orthology-driven discovery of antimicrobial drug targets in gut microbiome
-
LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
-
Learning Collective Variables from Time-lagged Generation
-
Learning Diffusion Models with Flexible Representation Guidance
-
Ligand Iterative Sampling for Affinity Refinement and Drug Discovery (LISARDD)
-
LLMs for Experiment Design in Scientific Domains: Are We There Yet?
-
Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
-
Minimum-Excess-Work Guidance
-
MINT: Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications
-
Mixtures of Neural Cellular Automata: A Stochastic Framework for Biological Growth Modelling
-
Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow
-
Modeling Molecular Sequences with Learning-Order Autoregressive Models
-
Molecular Cues to Smart Sequences: Optimizing Early Round SELEX Sequences
-
MolFORM: Multi-modal Flow Matching for Structure-Based Drug Design
-
MolGuidance: A Comparative Study of Guidance Methods for Conditional Molecule Generation
-
Multi-Granular Contrastive Alignment and Fusion for Fragment-Enhanced Virtual Screening
-
Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design
-
Multi-Objective-Guided Generative Design of mRNA with Therapeutic Properties
-
Multi-state Protein Design with DynamicMPNN
-
Multimodal Benchmarking of Foundation Model Representations for Cellular Perturbation Response Prediction
-
No Clear Winner at Small Scale: Comparing Modern Sequence Architectures and Training Strategies for Genomic Language Models
-
NovoMolGen: Rethinking Molecular Language Model Pretraining
-
NucleoBench: A Large-Scale Benchmark of Neural Nucleic Acid Design Algorithms
-
OrthoGraphRAG: Enhancing Clinical Decision Making with Multi-Level Knowledge Graphs
-
Partition Generative Modeling: Masked Modeling Without Masks
-
PhenoGraph: A Multi-Agent Framework for Phenotype-driven Discovery in Spatial Transcriptomics Data Augmented with Knowledge Graphs
-
Pi-SAGE: Permutation-invariant surface-aware graph encoder for binding affinity prediction
-
Predicting function of evolutionarily implausible DNA sequences
-
Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models
-
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
-
Promoter Sequence Generation using Homology Prompting
-
Protein Generator with Ribosomal Origin and Folding
-
ProteinCrow: A Language Model Agent That Can Design Proteins
-
ProVADA: Generating Subcellular Protein Variants via Ensemble-Guided Test-Time Steering
-
ProxelGen: Generating Proteins as 3D Densities
-
Pullback Flow Matching on Data Manifolds
-
Rapid and Reproducible Multimodal Biological Foundation Model Development with AIDO.ModelGenerator
-
Rapidash: Scalable Molecular Modeling Through Controlled Equivariance Breaking
-
Representing local protein environments with atomistic foundation models
-
Retrieval Augmented Protein Language Models for Protein Structure Prediction
-
Revisiting Sampling Strategies for Molecular Generation
-
Riemannian generative decoder
-
Robust Molecular Property Prediction via Densifying Scarce Labeled Data
-
Scaffold-Driven GPT Model for Drug Optimization
-
scAgents: A Multi-Agent Framework for Fully Autonomous End-to-End Single-Cell Perturbation Analysis
-
Scaling and Saturation Protein Language Models with Biological Data
-
Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data
-
Self-Supervised Representation Learning for Microbiome Improves Downstream Prediction in Data-Limited Settings and Cross-Cohort Generalizability
-
SIMBA-GNN: Simulation-augmented Microbiome Abundance Graph Neural Network
-
Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression
-
SMICE: enhanced conformational sampling using AlphaFold and coevolutionary information
-
SOAPIA: Siamese-Guided Generation of Off Target-Avoiding Protein Interactions with High Target Affinity
-
Sparse Autoencoders in Protein Engineering Campaigns: Steering and Model Diffing
-
Spatial Cell-Guided Pretraining for Scalable Spatial Transcriptomics Foundation Model
-
Straight but not so fast: Challenges with Rectified Flows in Protein Design.
-
Straight-Line Diffusion Model for Efficient 3D Molecular Generation
-
STRAND: Structure Refinement of RNA-Protein Complexes via Diffusion
-
SurfProp: A surface-based property prediction framework for antibody developability and screening
-
SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling
-
SynPair: Pairing Unpaired Antibody Chains at Billion-Sequence Scale With Contrastive Learning
-
TABASCO: A Fast, Simplified Model for Molecular Generation with Improved Physical Quality
-
TACTIC: An Explainable Multi-Agent Architecture for Classification & Interpretable Reasoning in Spatial Transcriptomics
-
Teddy: A FAMILY OF FOUNDATION MODELS FOR UNDERSTANDING SINGLE CELL BIOLOGY
-
Tissue Reassembly with Generative AI
-
To Optimize, Not to Invent: RNAGenScape for mRNA Sequence Generation and Optimization Without de novo Design
-
Torsional-GFN: a conditional conformation generator for small molecules
-
Towards functional annotation with latent protein language model features
-
Towards Molecular Conformer Generation with Language Models
-
ToxBench: A Binding Affinity Prediction Benchmark with AB-FEP-Calculated Labels for Human Estrogen Receptor Alpha
-
Trustworthy Inverse Molecular Design via Alignment with Molecular Dynamics
-
Two-Stage Pretraining for Molecular Property Prediction in the Wild
-
Unifying Force Prediction and Molecular Conformation Generation Through Representation Alignment
-
Unlocking Non-Invasive Brain-to-Text