Research map / Probabilistic and scientific modeling / Molecules and proteins
Quantum Transformer for Molecular Learning: Multi-Configuration Ground-State Energy Prediction
Yuichi Kamata, Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace classical Transformer with quantum attention (MQT) | Transformer · LiH PEC | average energy error: 6.0e-3 -> 3.5e-3 | Improved |
| replace classical Transformer with quantum attention (MQT) | Transformer · H4 PEC | average energy error: 1.9e-2 -> 0.5e-2 | Improved |
| replace classical Transformer with quantum attention (MQT) | Transformer · BeH2 PEC | average energy error: 3.3e-2 -> 2.7e-2 | Improved |
| replace classical Transformer with quantum attention (MQT) | Transformer · H2 PEC | average energy error: 9.3e-3 -> 8.9e-3 | No clear effect |
| add pretraining on H2, BeH2, H4 before few-shot fine-tuning on LiH (ablation) | MQT · LiH few-shot | average energy error: 7.6 × 10−3 -> 6.2×10−3 | Improved |
| use pretrained MQT zero-shot on LiH without fine-tuning (ablation) | MQT · LiH zero-shot | energy error | Hurt |
| use MQT instead of neural meta-VQE in few-shot | meta-VQE · LiH few-shot | average energy error: 7.0×10−3 -> 6.2×10−3 | Improved |
| increase classical Transformer embedding dim to 768 (ablation) | classical Transformer · LiH PEC | average energy error | No clear effect |
Closest papers by meaning
- WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction (ICML 2025 · similarity 0.85)
- GeoMFormer: A General Architecture for Geometric Molecular Representation Learning (ICML 2024 · similarity 0.85)
- MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra (ICLR 2025 · similarity 0.85)
- $\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials (NeurIPS 2024 · similarity 0.84)
- Quadratic Quantum Variational Monte Carlo (NeurIPS 2024 · similarity 0.84)
- QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
