Accepted Work

All accepted work 🌟 denotes Spotlight 👥💬 denotes RLSF

• An exploration of dataset bias in single-step retrosynthesis prediction

• GO-Diff: Data-free and amortized global structure optimization

• XDIP: A Curated X-ray Absorption Spectrum Dataset for Iron-Containing Proteins

• Continuous Uniqueness and Novelty Metrics for Generative Modeling of Inorganic Crystals

• Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems

• 👥💬 The Loss Landscape of XRD-Based Structure Optimization Is Too Rough for Gradient Descent

• 🌟 AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up

• Language Model Enabled Structure Prediction from Infrared Spectra of Mixtures

• 🌟 Automated Structure Elucidation at Human-Level Accuracy via a Multimodal Multitask Language Model

• Superior Molecular Representations from Intermediate Encoder Layers

• AMDEN: Amorphous Materials DEnoising Network

• Causal-Chemprop: Causal Machine Learning for Molecular Property Prediction and Optimization

• Emergent Pose-Invariance in 3D Molecular Representations via Multimodal Learning

• Benchmarking Multimodal Large Language Models on Electronic Structure Analysis and Interpretation

• 🌟 A Generative Diffusion Model for Amorphous Materials

• Enhancing UV Spectral Prediction through Auxiliary Task, Curriculum Learning, and Curvature Limitation

• Boltzina: Efficient and Accurate Virtual Screening via Docking-Guided Binding Prediction with Boltz-2

• NaviDiv: A Comprehensive Tool for Monitoring Chemical Diversity in Generative Molecular Design

• Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus

• 🌟 Language Models Enable Data-Augmented Inorganic Materials Synthesis Planning

• Efficient Nudged Elastic Band Method using Neural Network Bayesian Algorithm Execution

• 🌟 Migration as a Probe: A Generalizable Benchmark Framework for Specialist vs. Generalist Machine-Learned Force Fields

• One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra

• MatPROV: A Provenance Graph Dataset of Material Synthesis Extracted from Scientific Literature

• Enabling Accurate and Interpretable Property Prediction with TDiMS in Large Molecules

• LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modeling

• Accelerated Inorganic Materials Design with Generative AI Agents

• MLIPAudit: A benchmarking tool for Machine Learned Interatomic Potentials

• Evaluating Diffusion-Based Super-Resolution for Trustworthy Quantitative Metallography

• Solar-GECO: Perovskite Solar Cell Property Prediction with Geometric-Aware Co-Attention

• Integrating Experimental Expertise with Adaptive Bayesian Optimization for Perovskite Synthesis

• Concept-based Steering of Large Language Models for Conditional Molecular Generation

• 3DGrid-LLM: Token-Level Fusion of Language and 3D Grids for Chemical Multimodal Generation

• Training a Foundation Model for Materials on a Budget

• CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification

• Efficient Universal Potential Distillation with Pre-trained Students in LightPFP

• TopoMole: Topological Message Passing Meets Hyperedge Messages

• FORK: First-Order Relational Knowledge Distillation for Machine Learning Interatomic Potentials

• Training speedups via batching for geometric learning: an analysis of static and dynamic algorithms

• Benchmarking LLMs for atomic-level geometric manipulation in crystals

• Beyond Scaling: Chemical Intuition as Emergent Ability of Universal Machine Learning Interatomic Potentials

• Task Alignment Outweighs Framework Choice in Scientific LLM Agents

• Differentiable, model-agnostic free energy calculation

• GEOM-Drugs Revisited: Toward More Chemically Accurate Benchmarks for 3D Molecule Generation

• PolyBind: Effectively Combining Datasets Indexed in Different Representations of Polymers

• Q-CatNet: Leveraging Quantum and Graph Features for Catalyst Simulation and Discovery

• A Chemically Grounded Evaluation Framework for Generative Models in Materials Discovery

• 🌟 Universal Machine Learning Interatomic Potentials Enable Accurate Metal–Organic Framework Molecular Modeling

• Accelerating Material Discovery for Metal Organic Frameworks using Large Language Models

• Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study

• Accurate Band Gap Prediction in Porous Materials using Delta-Learning

• Scalable Low-Energy Molecular Conformer Generation with Quantum Mechanical Accuracy

• Fine-Tuning Vision-Language Models for Multimodal Polymer Property Prediction

• Neural Contrast Expansion for Explainable Structure-Property Prediction and Random Microstructure Design

• STR-Bamba: Multimodal Molecular Textual Representation Encoder-Decoder Foundation Model

• Factorial Data-Driven Inverse Design of Granular Hydrogels for Targeted Therapeutic Release

• Bridging data-rich and data-poor domains on Lithium-Ion Battery via Scanning Electron Microscopic data through Convolutional Neural Network Transfer Learning

• Surrogate Modeling for the Design of Optimal Lattice Structures using Tensor Completion

• An Effective Machine Learning Frame for Materials Discovery Structured by a Chemical Concept

• 🌟 GAP: Guided Diffusion for A Priori Transition State Sampling

• 👥💬 MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation

• A Physics-Informed Neural Network Approach to the Point Defect Model for Electrochemical Oxide Film Growth

• CHROMA: Conversational Human-Readable Optical Multilayer Assembly for Natural Language-Driven Inverse Design of Structural Coloration

• Symmetry-Aware Prediction of Electron Localization Functions from Superposed Atomic Densities

• Foundation Models Enabling Multi-Scale Battery Materials Discovery: From Molecules To Devices

• LLM Agents for Knowledge Discovery in Atomic Layer Processing

• Scaler Transfer: A Simple and Data-efficient Simulation-to-Real Transfer Scheme for Materials

• Benchmarking knowledge transfer methods in de novo materials discovery

• Towards End-to-End Learning of Protein Structure Prediction and Structure-based Sequence Design

• Physics-Constrained Diffusion for Lightweight Composite Material Design

• Benchmarking Agentic Systems in Automated Scientific Information Extraction with ChemX

• PolUQBench: A Benchmark Study on Uncertainty Quantification of Polymer Property Prediction

• Generalizable Prediction of Mixture Etching Rates Using Graph Neural Networks

• Data-driven prediction of polymer surface adhesion using high-throughput MD and hybrid network models

• Reciprocal Space Attention for Learning Long-Range Interactions

• AI-Guided Design and Discovery of Silicon-Based Anode Materials for Lithium-Ion Batteries

• A Computational Workflow for Cost-Effective Synthesis of Inorganic Materials: Integrating Thermodynamics, Cellular Automata, Machine Learning, and Commercial Databases

• Closed-loop, machine learning–driven optimization of reactor yields in reactive carbon electrolyzers

• Comparative analysis of model-agnostic explanation methods in materials science

• Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials

• 👥💬 Preference Learning from Physics-Based Feedback: Tuning Language Models to Design BCC/B2 Superalloys

• Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders

• 🌟 Inverse Design of Novel Superconductors via Guided Diffusion

• When Forces Disagree: A Data-Free Fast Uncertainty Estimate for Direct-Force Pre-trained Neural Network Potentials

• LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature

• WallpaperNet: A p6mm-Equivariant Graph Neural Network for Molecule Adsorption on Graphene

• 👥💬 LeMat-GenBench: Bridging the gap between crystal generation and materials discovery

• Hierarchical Deep Research with Local–Web RAG: Toward Automated System-Level Materials Discovery

• A Synthesizability-Guided Pipeline for Materials Discovery

• Cross Modal Predictive architecture for Material Property prediction

• CompGen: A Conditional Generation Framework for Inverse Composition Design of Catalytic Surfaces

• Accelerated Discovery of High-Performance Polyamines for Solid-State Direct CO2 Capture via Efficient Simulations and Bayesian Optimization

• 👥💬 SAM-EM: Real-Time Segmentation for Automated Liquid Phase Transmission Electron Microscopy

• Diversity-driven training of machine-learned force fields

• Interoperable Natural Language Interfaces for Self-Driving Labs via Model Context Protocol

• Direct Computation of Viscosity from Differentiable Atomistic Simulations

• Data Generation for Benchmarking Deep Learning on Materials Images via Noise Injection and CycleGAN

• Constrained Diffusion for Accelerated Structure Relaxation of Inorganic Solids with Point Defects

• MGB: The Material Generation Benchmark

• Additive Cook’s Distance Guided Training Set Reduction for Generalizable Foundation Models of Interatomic Potentials

• CHEMSETS: How Capable Are Chemistry LLMs?

• Multiscale and Multi-Timestep Switching of Multiple Machine Learning Force Fields for Artificial Intelligence-Driven Materials Simulations

• Towards Dynamic Benchmarks for Autonomous Materials Discovery

• PolyRecommender: A Multimodal Recommendation System for Polymer Discovery

• Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extraction

• Graph Neural Network Guided Selection of Functional Polymers for Charge Transfer Doping of 2D Materials

• PolyCG-Base: A Foundation Model for Universal, State-Aware Coarse-Graining of Linear Polymers

• Pharmacophore-Guided Generative Design of Novel Drug-Like Molecules

• ML-Driven Discovery of Metastable States

• Adapting General-Purpose Foundation Models for X-ray Ptychography in Low-Data Regimes

• Universally Converging Representations of Matter Across Scientific Foundation Models

• UFSMatAD: A Unified Framework for Few-Shot Material Anomaly Detection Across Nanofiber SEM and Wafer Imaging

• Sim-->Exp-MMNMR: A Benchmark for Simulation-to-Experiment Generalization in Multimodal NMR with Chemistry-Aware Metrics