ICML 2024 Past AI for science
ICML 2024 AI for Science Workshop
ICML2024-AI4Science
- Submission deadline
- May 26, 2024, 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 (156)
Fetched from OpenReview (v2) on 2026-06-10.
-
3D Reconstruction of Dark Matter Fields with Diffusion Models: Towards Application to Galaxy Surveys
-
A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series
-
A Fast Learning-Based Surrogate of Electrical Machines using a Reduced Basis
-
A Multi-View Mixture-of-Experts based on Language and Graphs for Molecular Properties Prediction
-
A Neural Material Point Method for Particle-based Simulations
-
Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators
-
Accelerating Simulation of Two-Phase Flows with Neural PDE Surrogates
-
Accelerating statistical inferences in astrophysics with Neural Networks and Hamiltonian Monte Carlo
-
Accounting for Selection Effects in Supernova Cosmology with Simulation-Based Inference and Hierarchical Bayesian Modelling
-
Active propulsion noise shaping for multi-rotor aircraft localization
-
AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion
-
An Advanced Physics-Informed Neural Operator for Comprehensive Design Optimization of Highly-Nonlinear Systems: An Aerospace Composites Processing Case Study
-
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
-
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
-
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
-
AstroPT: Scaling Large Observation Models for Astronomy
-
Bayesian Optimization for the Discovery of Redox Active Quinones
-
Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation
-
Boost Your Crystal Model with Denoising Pre-training
-
Causal Discovery over High-Dimensional Structured Hypothesis Spaces with Causal Graph Partitioning
-
Cell Morphology-Guided Small Molecule Generation with GFlowNets
-
Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
-
CodonMPNN for Organism Specific and Codon Optimal Inverse Folding
-
Consistent Validation for Predictive Methods in Spatial Settings
-
Constructing gauge-invariant neural networks for scientific applications
-
Cross-modality Matching and Prediction of Perturbation Responses with Labeled Gromov-Wasserstein Optimal Transport
-
Decoding Chemical Predictions: Group Contribution Methods for XAI
-
Deep Learning for Protein-Ligand Docking: Are We There Yet?
-
Diagnosing and fixing common problems in Bayesian optimization for molecule design
-
DiffusionPDE: Generative PDE-Solving Under Partial Observation
-
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
-
EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer
-
Efficiency and Transferability of Inductive Mondrian Conformal Predictors for Drug-Drug Synergy
-
Efficient 3D Molecular Generation with Flow Matching and Scale Optimal Transport
-
Efficient Evolutionary Search over Chemical Space with Large Language Models
-
EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction
-
Energy-Free Guidance of Geometric Diffusion Models for 3D Molecule Inverse Design
-
Enhancing Peak Assignment in CNMR Spectroscopy: A Novel Approach Using Multimodal Alignment
-
Enhancing Protein Design Robustness through Noise-Informed Sequence Design
-
Ensemble Guidance: Towards Generative 3D SBDD in Bioactive Chemical Spaces
-
Equation identification for fluid flows via physics-informed neural networks
-
EquiTorch: A Modularized Package for Flexibly Constructing Equivariant GNNs Building upon Pytorch-Geometric
-
Equivariant Neural Diffusion for Molecule Generation
-
Equivariant Transformer Forcefields for Molecular Conformer Generation
-
Euler operators for mis-specified physics-informed neural networks
-
Exploration and Application of AI in Space Science
-
Exploring Neural Scaling Laws in Molecular Pretraining with Synthetic Tasks
-
Fast-forward FARGO: Accelerating Protoplanetary Disk Simulations with Limited Data
-
Filling in the Gaps: LLM-Based Structured Data Generation from Semi-Structured Scientific Data
-
Flexible Docking via Unbalanced Flow Matching
-
Forecasting Smog Clouds With Deep Learning: A Proof-Of-Concept
-
Fourier Neural Operator based surrogates for $\textrm{CO}_2$ storage in realistic geologies
-
FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction
-
Gene Regulatory Network Inference from Pre-trained Single-Cell Transcriptomics Transformer with Joint Graph Learning
-
Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection
-
Generation and human-expert evaluation of interesting research ideas using knowledge graphs and large language models
-
Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs
-
Graph Multi-Similarity Learning for Molecular Property Prediction
-
GraphBPE: Molecular Graphs Meet Byte-Pair Encoding
-
Grappa - A Machine Learned Molecular Mechanics Force Field
-
Hyperspectral Unmixing for Raman Spectroscopy via Physics-Constrained Autoencoders
-
Impact4Cast: Forecasting high-impact research topics via machine learning on evolving knowledge graphs
-
Improving AlphaFlow for Efficient Protein Ensembles Generation
-
Improving the Accuracy of Coarse-grained Partial Differential Equations with Grid-based Reinforcement Learning
-
Inpainting crystal structure generations with score-based denoising
-
Inpainting Galaxy Counts onto N-Body Simulations over Multiple Cosmologies and Astrophysics
-
Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering
-
Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations
-
Knowledge Graph Extraction from Total Synthesis Documents
-
Large Language Models for Automated Open-domain Scientific Hypotheses Discovery
-
Large-Scale Discovery of Experimental Designs in Super-Resolution Microscopy with XLuminA
-
Learning cure kinetics of frontal polymerization PDEs using differentiable simulations
-
Learning Long Timescale in Molecular Dynamics by Nano-GPT
-
Learning the boundary-to-domain mapping using Lifting Product Fourier Neural Operators for partial differential equations
-
Local lateral connectivity is sufficient for replicating cortex-like topographical organization in deep neural networks
-
Many-Shot In-Context Learning for Molecular Inverse Design
-
Marrying Causal Representation Learning with Dynamical Systems for Science
-
Masking in Molecular Graphs Leveraging Reaction Context
-
MESS: Modern Electronic Structure Simulations
-
Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks
-
Meta-Designing Quantum Experiments with Language Models
-
MetaGFN: Exploring Distant Modes with Adapted Metadynamics for Continuous GFlowNets
-
Mind-to-Image: Projecting Visual Mental Imagination of the Brain from fMRI
-
Modeling Droplets Dynamics in Emulsions with Graph Neural Networks
-
MolGene-E: Inverse Molecular Design to Modulate Single Cell Transcriptomics
-
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
-
Multi-Frequency Progressive Refinement for Learned Inverse Scattering
-
Multi-task Extension of Geometrically Aligned Transfer Encoder
-
Navigating Chemical Space with Latent Flows
-
NCIDiff: Non-covalent Interaction-generative Diffusion Model for Improving Reliability of 3D Molecule Generation Inside Protein Pocket
-
NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries
-
Neural Incremental Data Assimilation
-
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
-
Non-Differentiable Diffusion Guidance for Improved Molecular Geometry
-
On the Effectiveness of Quantum Chemistry Pre-training for Pharmacological Property Prediction
-
Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking
-
PAIR: Boosting the Predictive Power of Protein Representations with a Corpus of Text Annotations
-
Parameter Tuning and Modeling of a Rotary Kiln using Physics-Informed Neural Networks
-
Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis
-
PathoLM: Identifying Pathogenicity From The DNA Sequence Through The Genome Foundation Model
-
Physics-Informed Neural Networks for Derivative-Constrained PDEs
-
Physics-Informed Weakly Supervised Learning for Interatomic Potentials
-
PIED: Physics-Informed Experimental Design For Inverse Problems
-
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
-
Population Transformer: Learning Population-level Representations of Intracranial Activity
-
Population-level Dark Energy Constraints from Strong Gravitational Lensing using Simulation-Based Inference
-
Predicting dark matter halo masses from simulated galaxy images and environments
-
Processing large-scale Graphs with G-Signatures
-
Projection Killer: peering through high dimensional posterior distribution
-
Prototype-Based Methods in Explainable AI and Emerging Opportunities in the Geosciences
-
Quantum circuit synthesis with diffusion models
-
RamanSPy: Augmenting Raman Spectroscopy Data Analysis with AI
-
Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems
-
Retrieve to Explain: Evidence-driven Predictions with Language Models
-
RNA-FrameFlow for de novo 3D RNA Backbone Design
-
RNAInvBench: Benchmark for the RNA Inverse Design Problem
-
Robust Learning of Transfer Functions for Single-Cell Transcriptomics Depth Normalization
-
Scalable Anomaly Detection in Batch Polishing Processes for Inertial Confinement Fusion Shells
-
Scalable Multi-Task Transfer Learning for Molecular Property Prediction
-
Scalable unsupervised alignment of metric and nonmetric structures
-
ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks
-
Scaling Automated Quantum Error Correction Discovery with Reinforcement Learning
-
Scaling Up Diffusion and Flow-based XGBoost Models
-
SE(3)-Equivariant Diffusion Graph Nets: Synthesizing Flow Fields by Denoising Invariant Latents on Graphs
-
Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion
-
Self-supervised learning for crystal property prediction via denoising
-
SemioLLM: Assessing Large Language Models for Semiological Analysis in Epilepsy Research
-
SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States
-
Smoke and Mirrors in Causal Downstream Tasks
-
Sorting Out Quantum Monte Carlo
-
Spectrum-Informed Multistage Neural Network: Multiscale Function Approximator of Machine Precision
-
Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate?
-
Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
-
Symbolic Regression with a Learned Concept Library
-
Synthetic Data-driven Prediction of Height for Childhood Malnutrition
-
Tail Extrapolation in target-aware conditional molecule generation
-
TarDis: Achieving Robust and Structured Disentanglement of Multiple Covariates
-
Task Addition in Multi-Task Learning by Geometrical Alignment
-
Text Serialization and Their Relationship with the Conventional Paradigms of Tabular Machine Learning
-
The Convolution-Closed Hurdle Motif With an Application to Tensor Decomposition
-
The Efficacy of Pre-training in Chemical Graph Out-of-distribution Generalization
-
The Scaling Law in Astronomical Time Series Data
-
Topological Neural Networks go Persistent, Equivariant and Continuous
-
Towards detailed and interpretable hybrid modeling of continental-scale bird migration
-
Towards Enforcing Hard Physics Constraints in Operator Learning Frameworks
-
Towards Reliable Uncertainty Estimates for Drug Discovery: A Large-scale Temporal Study of Probability Calibration
-
Training Compute-Optimal Protein Language Models
-
Training-free Design of Augmentations with Data-centric Principles
-
Transfer Learning in Multi-fidelity Surrogate Modeling: A Wind Farm Case
-
TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage
-
Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
-
Unfolding Time: Generative Modeling for Turbulent Flows in 4D
-
Unmixing Noise from Hawkes Process to Model Learned Physiological Events
-
UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation
-
Variable Star Light Curves in Koopman Space
-
Variational and Explanatory Neural Networks for Encoding Cancer Profiles and Predicting Drug Responses