paper-with-me

홈 › Papers

Frame-based Equivariant Diffusion Models for 3D Molecular Generation

2025-09-23 · Mohan Guo, Cong Liu, Patrick Forré arxiv

Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We propose a frame-based diffusion paradigm that achieves deterministic E(3)-equivariance while decoupling symmetry handling from the backbone. Building on this paradigm, we investigate three variants: Global Frame Diffusion (GFD), which assigns a shared molecular frame; Local Frame Diffusion (LFD), which constructs node-specific frames and benefits from additional alignment constraints; and Invariant Frame Diffusion (IFD), which relies on pre-canonicalized invariant representations. To enhance expressivity, we further utilize EdgeDiT, a Diffusion Transformer with edge-aware attention. On the QM9 dataset, GFD with EdgeDiT achieves state-of-the-art performance, with a test NLL of -137.97 at standard scale and -141.85 at double scale, alongside atom stability of 98.98%, and molecular stability of 90.51%. These results surpass all equivariant baselines while maintaining high validity and uniqueness and nearly 2x faster sampling compared to EDM. Altogether, our study establishes frame-based diffusion as a scalable, flexible, and physically grounded paradigm for molecular generation, highlighting the critical role of global structure preservation.

📄 PDF Abstract BibTeX arXiv:2509.19506

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models

2024-04-21 · Romain Lacombe, Neal Vaidya

Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by build…

Drug Discovery

Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space

2024-06-15 · Mohamed Amine Ketata, Nicholas Gao, Johanna Sommer, Tom Wollschläger 외

We introduce a new framework for molecular graph generation with 3D molecular generative models. Our Synthetic Coordinate Embedding (SyCo) framework maps molecular graphs to Euclidean point clouds via synthetic conformer…

Edge ClassificationGraph GenerationGraph Neural NetworkMolecular Graph Generation+1

EC-Conf: An Ultra-fast Diffusion Model for Molecular Conformation Generation with Equivariant Consistency

2023-08-01 · Zhiguang Fan, Yuedong Yang, Mingyuan Xu, Hongming Chen

Despite recent advancement in 3D molecule conformation generation driven by diffusion models, its high computational cost in iterative diffusion/denoising process limits its application. In this paper, an equivariant con…

Denoising

Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation

2025-08-22 · Zhijian Zhou, Junyi An, Zongkai Liu, Yunfei Shi 외 arxiv

Generating physically realistic 3D molecular structures remains a core challenge in molecular generative modeling. While diffusion models equipped with equivariant neural networks have made progress in capturing molecula…

Reinforcement Learning

Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation

2026-03-10 · Junyi An, Chao Qu, Yun-Fei Shi, Zhijian Zhou 외 arxiv

Recent 3D molecular generation methods primarily use asynchronous auto-regressive or synchronous diffusion models. While auto-regressive models build molecules sequentially, they're limited by a short horizon and a discr…