ICML 2024 paper list for Ai4Sci
| Category | Title | Conference | Note |
|---|---|---|---|
| protein | Kernel-Based Evaluation of Conditional Biological Sequence Models | ICML24 | |
| protein | Diffusion Language Models Are Versatile Protein Learners | ICML24 | |
| protein | CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model | ICML24 | |
| protein | Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints | ICML24 | |
| protein | Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization | ICML24 | |
| protein | Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning | ICML24 | |
| protein | Protein Conformation Generation via Force-Guided SE(3) Diffusion Models | ICML24 | |
| protein | Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates | ICML24 | |
| protein | Knowledge-aware Reinforced Language Models for Protein Directed Evolution | ICML24 | |
| protein | Feedback Efficient Online Fine-Tuning of Diffusion Models | ICML24 | |
| protein | Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning | ICML24 | |
| protein | Prospector Heads: Generalized Feature Attribution for Large Models & Data | ICML24 | |
| protein | Network Tight Community Detection | ICML24 | |
| protein | Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models | ICML24 | |
| protein | Evolution-Inspired Loss Functions for Protein Representation Learning | ICML24 | |
| protein | FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames | ICML24 | Spotlight |
| protein | Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chains | ICML24 | |
| protein | Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning | ICML24 | |
| protein | Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space | ICML24 | Spotlight |
| protein | SurfPro: Functional Protein Design Based on Continuous Surface | ICML24 | |
| protein | ESM All-Atom: Multi-Scale Protein Language Model for Unified Molecular Modeling | ICML24 | |
| protein | CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes | ICML24 | |
| protein | Floating Anchor Diffusion Model for Multi-motif Scaffolding | ICML24 | |
| protein | Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design | ICML24 | |
| protein | Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency | ICML24 | |
| protein | Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation | ICML24 | |
| protein | Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding | ICML24 | |
| protein | Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design | ICML24 | |
| molecul | Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks | ICML24 | |
| molecul | Mol-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective | ICML24 | |
| molecul | Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction | ICML24 | |
| molecul | Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation | ICML24 | |
| molecul | Interpreting Equivariant Representations | ICML24 | |
| molecul | Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers | ICML24 | |
| molecul | Data-Efficient Molecular Generation with Hierarchical Textual Inversion | ICML24 | |
| molecul | Generative Marginalization Models | ICML24 | |
| molecul | Expressivity and Generalization: Fragment-Biases for Molecular GNNs | ICML24 | Oral |
| molecul | Joint Composite Latent Space Bayesian Optimization | ICML24 | |
| molecul | Representing Molecules as Random Walks Over Interpretable Grammars | ICML24 | Spotlight |
| molecul | Weisfeiler Leman for Euclidean Equivariant Machine Learning | ICML24 | |
| molecul | D-Flow: Differentiating through Flows for Controlled Generation | ICML24 | |
| molecul | DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents | ICML24 | |
| molecul | Diffusive Gibbs Sampling | ICML24 | |
| molecul | Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge | ICML24 | Spotlight |
| molecul | Aligning Transformers with Weisfeiler-Leman | ICML24 | |
| molecul | Topological Neural Networks go Persistent, Equivariant, and Continuous | ICML24 | |
| molecul | Learning Exceptional Subgroups by End-to-End Maximizing KL-Divergence | ICML24 | Spotlight |
| molecul | Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations | ICML24 | |
| molecul | Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction | ICML24 | |
| molecul | UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning | ICML24 | |
| molecul | A Graph is Worth Words: Euclideanizing Graph using Pure Transformer | ICML24 | |
| molecul | Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization | ICML24 | |
| molecul | On the Generalization of Equivariant Graph Neural Networks | ICML24 | |
| molecul | Solving Poisson Equations using Neural Walk-on-Spheres | ICML24 | |
| molecul | LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery | ICML24 | |
| molecul | Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces | ICML24 | |
| molecul | Graph Generation with Diffusion Mixture | ICML24 | |
| molecul | Equivariant Graph Neural Operator for Modeling 3D Dynamics | ICML24 | |
| molecul | GeoMFormer: A General Architecture for Geometric Molecular Representation Learning | ICML24 | |
| molecul | Swallowing the Bitter Pill: Simplified Scalable Conformer Generation | ICML24 | |
| molecul | Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models | ICML24 | Oral |
| molecul | Projecting Molecules into Synthesizable Chemical Spaces | ICML24 | |
| drug | Entropy-Reinforced Planning with Large Language Models for Drug Discovery | ICML24 | |
| drug | Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process | ICML24 | |
| drug | Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design | ICML24 | |
| drug | Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants | ICML24 | |
| drug | MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space | ICML24 | |
| drug | Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion | ICML24 | |
| drug | WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer | ICML24 | |
| drug | Full-Atom Peptide Design based on Multi-modal Flow Matching | ICML24 | |
| drug | PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching | ICML24 | |
| drug | Predicting Dose-Response Curves with Deep Neural Networks | ICML24 | |
| drug | Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains | ICML24 | |
| drug | Quantum Theory and Application of Contextual Optimal Transport | ICML24 | |
| drug | Structure-based drug design by denoising voxel grids | ICML24 | |
| drug | Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design | ICML24 | |
| drug | EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction | ICML24 | Oral |
| drug | Improving Antibody Humanness Prediction using Patent Data | ICML24 | |
| drug | Drug Discovery with Dynamic Goal-aware Fragments | ICML24 | |
| drug | Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation | ICML24 | |
| materials | Language Models as Science Tutors | ICML24 | |
| materials | Unveiling the Potential of AI for Nanomaterial Morphology Prediction | ICML24 | |
| materials | Fool Your (Vision and) Language Model with Embarrassingly Simple Permutations | ICML24 | |
| materials | Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity | ICML24 | |
| materials | Copyright Traps for Large Language Models | ICML24 | |
| materials | Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks | ICML24 | |
| materials | FlowMM: Generating Materials with Riemannian Flow Matching | ICML24 | |
| materials | Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy | ICML24 | Oral |
| materials | PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling | ICML24 | |
| materials | Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning | ICML24 | |
| materials | Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning | ICML24 | |
| materials | A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction | ICML24 | |
| materials | A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules? | ICML24 | |
| materials | Outlier-aware Slicing for Post-Training Quantization in Vision Transformer | ICML24 | |
| materials | INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer | ICML24 | |
| DNA | Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling | ICML24 | |
| DNA | DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation | ICML24 | |
| DNA | Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs ``Difficult" Downstream Tasks in LLMs | ICML24 | |
| DNA | Dirichlet Flow Matching with Applications to DNA Sequence Design | ICML24 | |
| DNA | DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation | ICML24 | |
| RNA | RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching | ICML24 | |
| RNA | Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency | ICML24 | |
| RNA | Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem | ICML24 | |
| RNA | Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective | ICML24 | |
| conformation | AlphaFold Meets Flow Matching for Generating Protein Ensembles | ICML24 | Oral |
| electronic | Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast | ICML24 | |
| electronic | BetterV: Controlled Verilog Generation with Discriminative Guidance | ICML24 | |
| electronic | LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits | ICML24 | |
| electronic | Exploiting Negative Samples: A Catalyst for Cohort Discovery in Healthcare Analytics | ICML24 | |
| electronic | Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources | ICML24 | |
| chemical | Structured Chemistry Reasoning with Large Language Models | ICML24 | |
| chemical | CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback | ICML24 | |
| chemical | Learning Surrogates for Offline Black-Box Optimization via Gradient Matching | ICML24 | |
| chemical | E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning | ICML24 | |
| chemical | Learning to Scale Logits for Temperature-Conditional GFlowNets | ICML24 | |
| chemical | OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning | ICML24 | |
| chemical | Gaussian Plane-Wave Neural Operator for Electron Density Estimation | ICML24 | |
| chemical | The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning | ICML24 |