ICLR 2026PastLarge language modelsAI for science
ICLR 2026 Workshop on Foundation Models for Science: Real-World Impact and Science-First Design
ICLR 2026 Workshop FM4Science
- Submission deadline
- Feb 11, 2026, 11:59 UTCOpenReview-synced 2026-02-11 11:59 UTC (as of 2026-06-30) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (78)
Fetched from OpenReview (v2) on 2026-06-10.
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
[Short] Real-Time Explanations for Tabular Foundation Models
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Accurate Tokenization of 3D Small Organic Molecules
Agentic Discovery of Multi-Channel Bioacoustic Association Algorithms
AI Driven Discovery of Bio Ecological Mediation in Cascading Heatwave Risks
Augmenting representations with scientific papers
Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models
Benchmarking foundation models for unsupervised discovery in large multimodal astrophysical datasets
Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography
Built-in Safeguards for Auto-regressive Protein Foundation Models through Self-play
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
Constructing Machine-Precision Neural Networks with Quasi-Interpolants
Darwin-7B: A Multi-Omic Foundation Model for the Human Gut Microbiome\\via Sparsified Quality-Aware Tokenization
Deep Learning for BioImaging: What Are We Learning?
Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution
ECLIPSE: A Composable Pipeline for Predicting ecDNA Formation, Evolution, and Therapeutic Vulnerabilities in Cancer
Effective Biological Representation Learning by Masking Gene Expression
Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
Evaluating Expert Specialization in Mixture-of-Experts Antibody Language Models
EVIDENCE-GATED SCIENTIFIC QA WITH EXPLICIT ABSTENTION AND PAGE-LEVEL PROVENANCE
EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering
FINGERS-7B: A Multi-Omic Foundation Model for Precision Biomarker Discovery
FIRE: Multi-fidelity Regression with Distribution-conditioned In-context Learning using Tabular Foundation Models
FlowMS: Flow Matching for De Novo Structure Elucidation from Mass Spectra
Foundation Model for Cardiac Time Series via Masked Latent Attention
Foundation Models as Physical Priors: Decoupling Geometric Reasoning from Small-Molecule Solubility Prediction
Foundation models for agricultural sciences - Challenges and opportunities
FragmentFlow: Scalable Transition State Generation for Large Molecules
From Weather to Weathering: Foundation Models for Carbon Removal via Rock Weathering
Full-length mRNA Design with Reward-Guided Masked Diffusion Model Fine-Tuning
GeoPT: Scaling Physics Simulation via Lifted Geometric Pre-Training
Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
Higher-order grammar representations for molecular generation and learning
Information-Theoretic Requirements for Gradient-Based Task Affinity Estimation in Multi-Task Learning
Kraus Constrained Sequence Learning For Quantum Trajectories from Continuous Measurement
Language-Enhanced Representation Learning for Single-Cell Transcriptomics
Learning Enhanced Protein Representations from Molecular Dynamics Trajectories via Temporal GNNs
Learning What's Real: Disentangling Signal and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics
LUMINA: Foundation Models for Topology Transferable ACOPF
LunarFM: a multimodal representation of the Moon's surface
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery
MOOSE: Targeted Small Molecule Generation via Multi-Objective-Guided Discrete Diffusion
Multimodal Datasets with Controllable Mutual Information
Neural Scaling Laws for Boosted Jet Tagging
NeuroLoom: Modeling Cortical Microcircuits with Spiking Neural Networks
On Neural Scaling Laws for Weather Emulation through Continual Training
Optimizing Materials With CliqueFlowmer
PepRePs: Peptide-Retargeted Phosphatases via Generative Language Models
Position: Science is Collaborative—LLM for Science Should Be Too
Predicting New Concept--Object Associations in Astronomy by Mining the Literature
Rethinking Perturbation Prediction Baselines
SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
Self-Attention for Quantum Entanglement Prediction
SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework
Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
SNOOPPI: Sequence-Normalized Database of On- and Off-Target Protein-Protein Interactions
Sparse Probes, Murky Physics: Interpretability Challenges in a Foundation Model for Continuum Dynamics
ST-Align: Multi-Scale Image-Gene Foundation Modeling for Spatial Transcriptomics via Spot-Niche Alignment
Surrogate-Assisted Pedestrian Protection Design via a Foundation Model–Orchestrated Workflow
Symmetry-Aware Entropy Reinforcement Learning for Chaos Accurate Holographic Duals in NISQ Hardware
Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra
The Reliability Gap in Agentic Evidence Verification for Materials Science
The Right Inductive Bias for the Job: Dependency-Aware Masking for Scientific Foundation Models
Towards Foundation Models for Quantum Unitary Synthesis via Zero-Shot MDL
Towards Understanding Hybrid Protein Language Model Design: A Systematic Ablation and Interpretability Study
Two-Stage Ligand-Protein Complex Sequence Design with L-Caliby
Understanding The Limits Of Text-Only Molecular Reasoning: A Case Study In Synthetic Chain-Of-Thought Supervision
Unified Cross-Scale 3D Generation and Understanding via Autoregressive Modeling
Vehicle Surface Pressure Prediction from 2D Sketches via a Pre-Trained Diffusion Model
Want to train KANS at scale? Now UKAN!
When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction
When Protein Dynamics Matter: Integrating Molecular Dynamics into Protein Foundation Models
WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling
Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials