Tag
This paper introduces BDIP-Net, a graph neural network for predicting properties of bilayer materials by explicitly modeling intra-layer and inter-layer interactions, and presents a framework for efficient structure optimization using MatterSim-D3.
This paper introduces MR-MoL, a multi-granular rationale-guided molecular LLM that exposes GNN-derived substructure attributions to improve molecular property prediction on MoleculeNet benchmarks.
SenCos-GEM introduces a physics-guided molecular representation learning framework that uses Squeeze-and-Excitation modules and a law-of-cosines constraint to improve 3D geometric understanding, achieving state-of-the-art results on MoleculeNet regression benchmarks.
A researcher describes building a deep learning model with 270k parameters to predict melting points from topological indices, achieving R² 0.6399, and asks whether to publish the results.
PolyFusionAgent is a framework that combines a multimodal polymer foundation model (PolyFusion) with a tool-augmented, literature-grounded design agent (PolyAgent) for polymer property prediction and inverse design, enabling evidence-linked discovery.