CliffordSTF couples Clifford multivectors to rank-2 and rank-3 symmetric-traceless tensor tracks through bilinear cross-track contractions, lifting force cosine similarity from 0.055 to 0.551 on rMD17 while outperforming CG-free baselines.
arXiv preprint arXiv:2011.14115 (2020)
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
years
2026 10representative citing papers
Extends the mol-infer MILP framework to copolymers via a mixing vector representation, trains ML predictors achieving R^2 >0.7 on 9/10 datasets, and shows tractable multi-monomer inverse design with external consistency checks.
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
FB-GNN-MBE integrates fragment-based graph neural networks into many-body expansion to predict two- and three-body energies for water, phenol, and mixture systems at chemical accuracy, with a teacher-student protocol enabling transfer to new cluster sizes without full retraining.
SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.
A tensor-channel equivariant GNN based on PaiNN propagates symmetric rank-2 tensor features during message passing and achieves lower full-tensor and anisotropic error than readout-only and MACE baselines on QM7-X geometries.
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.
citing papers explorer
No citing papers match the current filters.