ICML 2026 Past AgentsGenerative models
The 2026 Workshop on Generative and Agentic AI for Biology
GenBio 2026
- Submission deadline
- May 9, 2026, 12:00 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 (153)
Fetched from OpenReview (v2) on 2026-06-10.
-
3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows
-
A Deep Generative Mixture Model for Enhancing Circulating Tumor DNA Estimation
-
A supervised ontology-aware cell annotation method for single-cell transcriptomic data
-
ACER: Towards Generalizable Protein-ligand Co-folding
-
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
-
Affinage: Genome-Scale Mechanistic Gene Annotation from the Published Literature
-
Agent-Guided De Novo Design of Nanobody Binders Against a Novel Cancer Target
-
Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3
-
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
-
AIR: Inference-Time Refinement for Discrete-Diffusion Antibody Humanization
-
AIVARI Agent: An Evidence-Grounded Agentic LLM for Variant Reportability and Interpretation
-
AlloGen: Conformation-Selective Binder Design with Differential State Scoring
-
AMP-DiT: Antimicrobial Peptide Design with AMP-classifier Conditional Diffusion Transformers
-
annDNA: Learning Annotation-Aware Genomic Representations via Knowledge Distillation
-
AnomalyModifier: Suppressor Modifier Discovery in Familial Hypercholesterolemia via One-Class Anomaly Detection
-
Antibody Generation via Redistributed Latent Diffusion
-
Ares: Loss-Free Mixture-of-Experts Routing for Bidirectional Protein Encoders
-
AURORA: Alignment-Guided Mutation Proposal for Protein Engineering
-
Autoregressive Models Enable Efficient Conditional 3D Molecular Generation
-
Base-and-Sugar Dual-Frame Flow Matching for RNA Co-Design
-
Beyond Nativeness: Viral Proteins in Protein Language Models
-
BGC-Master: Detecting Novel Biosynthetic Gene Clusters with DNA Foundation Models
-
BioSkillSafety: A Systematic Benchmark for Evaluating Agent Skill Safety in Bioinformatics
-
bish-bash-fold: what are protein structure prediction models learning?
-
Boltz-1 as a force field -- why co-folding models struggle with learning physics and how to fix it
-
Boltz-Jump: Accelerated Sampling of the Conformational Landscape of Biomolecular Structure Prediction Models
-
Boltz-Perturb: The Path Not Taken. Unlocking Generative Diversity in Co-Folding Models via Training-Free Conditioning Perturbation
-
Bridging Gene Regulatory Networks and Causal Representation Learning in Single-Cell Genomics Data
-
Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
-
Can AI Scientists Discover Neural Mechanisms? Evaluating Agentic Biological Discovery in a Digital Fly.
-
Canopy: A Heterograph Foundation Model for Metabolic Engineering
-
Cell-Level Virtual Screening
-
CIDER: Conformal Information-Directed Agents for Low-Budget Protein Engineering
-
CLAMP: Steady-State ODE Inference of Gene Regulatory Networks from Single-Cell Perturbations
-
Coder as Editor: Code-driven Interpretable Molecular Editing
-
COMPASS: Decoupled Latent Steering for Protein Conformational Transitions
-
Confidence-Weighted Elastic Gaussian Networks To Predict Protein Flexibility
-
ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
-
Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment
-
CPgen: Heterochiral Cyclic Peptide Ensemble Generation and Ensemble-Based Sequence Design
-
CupOFLATTE: Coupled Objective-Guided Discrete Flows via Linker Assembly for Targeted PROTAC Engineering
-
DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Model
-
De Novo Generation of Odorant Molecules with Targeted Olfactory Receptor Activation Patterns
-
Decoding Loss-of-Function Variants with Sparse Concept Features of ESM-2
-
Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes
-
DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts
-
DELBERT-2: Pretrained Fingerprint Language Models for DEL Protein Binder Prediction
-
Density-guided AlphaFold reveals unmodeled alternative turn conformations in protein structures
-
Design-CP: Context Parallelism for Design of Protein Nanoparticles
-
Diamond Maps for Protein Binder Design: Inference-Time Scaling Survives Stochastic Flow Map Distillation
-
DNA Compression with Genomic Language Models: Tokenization, Benchmarking, and an Information-Content Map
-
DrugSAGE: Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
-
ELISA: An Interpretable Hybrid Generative AI Agent for Expression-Grounded Discovery in Single-Cell Genomics
-
Elucidating the Design Space of Generative Models for Single-Cell Perturbation Prediction
-
EpiCLIP: Learning Antibody-Antigen Interactions from Approximate Interfaces
-
Evaluating H5N1 Vaccine Durability using Computationally-Designed Proteins
-
Evaluating out of distribution generalization of protein language models
-
Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design
-
EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation
-
Factorized Search and Cartography of Synthon-Based Chemical Spaces
-
Few-Step Cofolding with All-Atom Flow Maps
-
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
-
GDTR: Layer-wise Settling Depth Reveals Biological Grammar in Genomic Foundation Models
-
GEMS: Molecular Structure Identification via Geodesic Navigation of the Isomer Manifold
-
Gene-Embedding Perturbation Operators for Zero-Shot and Transferable Prediction of Transcriptional Responses
-
Generalise or Memorise? Benchmarking Ligand-Conditioned Protein Generation
-
Generalization of Protein Foundation Models for Engineered Fluorescent Biosensors
-
Generating and decoding methylated DNA with a Human Epigenetic Foundation Model
-
Generative design of intrinsically disordered protein regions with IDiom
-
Generative Modeling of Solvated Biomolecules
-
Generative Priors for Cryo-EM Image Reconstruction
-
GeoRecon: Graph-Level Representation Learning for 3D Molecules via Reconstruction-Based Pretraining
-
GOAgent: Tool-Orchestrating Language Agents for Protein Function Annotation
-
GPA: Generative Population Annealing for Test-Time Sequence Design
-
Harmonic Torsional Diffusion for Protein-Ligand Flexible Docking
-
Hepa-RAFT: Retrieval-Augmented Virtual Hepatocyte Responses for Hepatotoxicity Prediction
-
How Do Co-folding Models Organize Structural Information?
-
Hybrid Flow Matching in Billera-Holmes-Vogtmann Tree Space for Generative Phylogenetic Inference
-
Identification of Heterogeneous Erlotinib Response Gene Sets Using Sample-Specific Counterfactual Causal Attribution
-
Improving the Efficacy of Test-Time Steering in Masked Diffusion Models with Parallel Tempering
-
IRIS: An Agentic Multi-Phase Framework for Automated Scientific Literature Review
-
IsoPLM: Isolating the Impacts of Architecture on Protein Language Models
-
Just Add Structure: Protein Language Models Combined with Structural Equivariance Excel at Protein Tasks
-
Knowing When to Stop: Pertura for Graph-Enforced PI Gating in Perturb-seq Agents
-
Large-scale sequence modeling of antibody-antigen binding specificity
-
Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents
-
LeFlur: A Biomolecular Design Model with Latent Structure Tokens
-
LLM-Assisted versus Agentic Approaches to De Novo Minibinder Design for a KRAS G12D Neoantigen
-
LLM-guided acquisition improves pathway-specific Perturb-seq design under experimental budgets
-
MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery
-
Measure-to-measure Regression with Transformers
-
Mechanisms Matter: Transportability of Cellular Perturbation Effects
-
MoCDiff: Efficient Motif-Constrained Discrete Diffusion for Molecule Generation
-
MolOpt-Eval: Can Frontier LLMs Perform Structure-Based Hit-to-Lead Optimization?
-
MotifCraft: scalable functional protein binder design with AlphaFold2 hallucination
-
Multi-Scale Flow Matching for Continuous-time Generative Modeling of Spatiotemporal Tissue Dynamics from Spatial Transcriptomics
-
NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling
-
Natural-Language-Guided Generator-Agnostic Shortlisting for Protein Binder Design
-
Order-Agnostic Decoding for Sample-Efficient RNA Inverse Folding
-
PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
-
PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
-
Phase-Calibrated Steering of Protein Diffusion Language Models
-
Phenotype-Conditioned Drug Repurposing for Undiagnosed Rare Disease Patients via Graph Neural Networks and LLM Hybridization
-
PIGEON: Pocket-Inferred Geometric Ensemble Flexible Docking
-
PlasmidLM: A Promptable DNA Language Model via Verifiable-Reward Post-Training
-
pLM-Guided Inverse Folding for Antibody Sequence Design
-
Position: AI for Drug Discovery Models Often Do Not Learn as Expected and How to Diagnose These Failure Modes
-
PRiMeFlow: capturing complex expression heterogeneity in perturbation response modelling
-
Probing coexistence of robust threshold and ultrasensitivity in molecular switches and cascades
-
Progressive Multi-Agent Reasoning for Biological Perturbation Prediction
-
PROPHET: Phylogenetically Robust Antiviral Peptide Design Against Heterogeneous Evolutionary Trajectories
-
Proteo-R1: Reasoning Foundation Models for De Novo Antibody Design
-
ProteomeLM: A Proteome-Scale Language Model Enables Accurate and Rapid Prediction of Protein-Protein Interactions and Gene Essentiality Across Taxa
-
Proteomic Divergence in the Trisomic Mouse Cortex: Machine Learning Identifies Tau, APP, and ADARB1 as Key Genotype Signatures and Reveals Limited Proteomic Response to Memantine
-
ProtoCol: Late Interaction Retrieval for Protein Homolog Search
-
ProtQueSt: Query-Conditioned Retrieval-Augmented Generation for Protein Function Annotation
-
Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
-
Representative vs. Load-bearing Layers: A Dissociation in Genomic Foundation Models
-
Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation
-
Rethinking Self-Consistency in Protein Generative Models
-
RobustDock: Robust Generative Flexible Docking with Long-Tailed Data
-
Scaling Pocket Docking with Data Augmentation and Heterogeneous Equivariant Graph Attention
-
Self-Distillation for Continual Learning in Masked Language Models
-
Self-Supervised Contextual Representation Learning for Transcriptomic Generative AI
-
Shifting a Molecular Generator Toward Developability with Iterative Importance Fine-Tuning
-
SICD: Measuring Semantic Surrender and Epistemic Resistance Under Biomedical Interference
-
Simplified motif background model provides significant speed-up for regulatory activity inference
-
Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
-
SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?
-
SOAPIA: Specificity-Guided Generation of Off-Target-Avoiding Protein Interactions with High Target Affinity
-
Spectral Diffusion for Protein Dynamics
-
SPROUT: Steered Plant Promoter Editing via Rollout-Guided Utility Tilting of Edit Flows
-
ST-JEPA: Joint-Embedding Predictive Architecture for Spatial Transcriptomics
-
Steering Sequence Generation in Protein Language Models through Iterative Lookback Monte Carlo Sampling
-
Stochastic Path Integral Formalism of Causal Field Theory
-
Structure-Guided Reinforcement Learning for High-Affinity Antibody Design
-
SurfDesign: Effective Protein Design on Molecular Surfaces
-
Synthesis Tamper-evident Attestation and Molecular Provenance (STAMP): Cryptographic Molecular Barcoding for DNA Synthesizers
-
Synthon Contrastive Learning for Synthesizable 3D Molecule Generation
-
SynthonBench: Benchmarking Sample-Efficient Optimization in Combinatorial Chemical Spaces
-
The Hallucination Dependence Index: A Cross-Condition Diagnostic for Clinical-LLM Faithfulness
-
Token-Only Adaptation of Frozen Self-Supervised Vision Foundation Models for Cross-Species Animal Pose: A Pareto-Frontier Characterization Across Eight Held-Out Mammal Species
-
Token-Wise Residual Latent Adapters: Steering Seq2Seq Models for Protein Fitness Extrapolation
-
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
-
Towards an Agentic AI Framework for Generating, Optimizing and Filtering Protein Binders
-
Towards Autonomous Mechanistic Reasoning in Virtual Cells
-
Toxin Feature Hierarchy in ESM-2: Mechanistic Interpretability reveals Why Frozen Probes Resist ProteinMPNN Redesign
-
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
-
Uncertainty-Aware Oracle-Concordance Steering for Reliable Generative Design
-
Unified sampling framework and benchmarking of sequence- and structure-based protein models
-
VarLitBench and VarLitAgent for Benchmarking and Automating LLM-Assisted Functional Evidence Curation in Genomic Variant Interpretation
-
What Does a Chromatin Foundation Model Know About a Petri Dish? Sparse Autoencoders Reveal In Vitro vs. In Vivo Context in EPIBERT
-
Where Simple Baselines Fail: Mapping the Modeling Frontier of Perturbation Prediction