2026 Harnessing homolytic bond energetics to steer inverse radical design Treating bond dissociation energy as a continuous generative coordinate to steer radical molecular design Data-driven massive reaction networks reveal new pathways underlying catalytic CO₂ hydrogenation Automated discovery of catalytic pathways via DFT, ML-predicted barriers, and human-intelligence-inspired reaction enumeration 2025 Knowledge Distillation for Molecular Property Prediction: A Scalability Analysis Compressing large graph neural networks into efficient student models without sacrificing predictive accuracy Molecular Representation Learning: Cross-domain Foundations and Future Frontiers A comprehensive review of deep learning-based molecular representations spanning GNNs, transformers, diffusion models, and contrastive learning Rethinking Retrosynthesis: Curriculum Learning Reshapes Transformer-Based Small-Molecule Reaction Prediction Reshaping reaction prediction by controlling training difficulty with a chemically informed curriculum learning framework A kinetic model for the direct thermal liquefaction of pine wood Reaction network and quantitative kinetic model for lignocellulosic biomass conversion via direct thermal liquefaction 2024 Probing Ion Effects In Nanoconfined Aqueous Electrolytes: A Molecular Dynamics Study Using Neural Network Potentials DFT-accurate machine learning potentials for molecular dynamics simulations of ion behavior in confined aqueous electrolytes 2022 Tailoring nanoporous graphene via machine learning: Predicting probabilities and formation times of arbitrary nanopore shapes Predicting nanopore formation probability and time in graphene using a two-stage ML framework on kinetic Monte Carlo data Vehicle Smoke Synthesis and Attention-based Deep Approach for Vehicle Smoke Detection Boosting surveillance-based vehicular emission detection with transformer attention and synthetic data augmentation
