REVIEW 11 cited by
FlowMM: Generating Materials with Riemannian Flow Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Crystalline materials are a fundamental component in next-generation technologies, yet modeling their distribution presents unique computational challenges. Of the plausible arrangements of atoms in a periodic lattice only a vanishingly small percentage are thermodynamically stable, which is a key indicator of the materials that can be experimentally realized. Two fundamental tasks in this area are to (a) predict the stable crystal structure of a known composition of elements and (b) propose novel compositions along with their stable structures. We present FlowMM, a pair of generative models that achieve state-of-the-art performance on both tasks while being more efficient and more flexible than competing methods. We generalize Riemannian Flow Matching to suit the symmetries inherent to crystals: translation, rotation, permutation, and periodic boundary conditions. Our framework enables the freedom to choose the flow base distributions, drastically simplifying the problem of learning crystal structures compared with diffusion models. In addition to standard benchmarks, we validate FlowMM's generated structures with quantum chemistry calculations, demonstrating that it is about 3x more efficient, in terms of integration steps, at finding stable materials compared to previous open methods.
Forward citations
Cited by 11 Pith papers
-
PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design
PLaID++ generates inorganic crystal structures as Wyckoff-position text and uses iterative direct preference optimization on an interatomic-potential stability reward, reaching a 7.74% stable-unique-novel rate on MP-2...
-
Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
SbCD is a crystal diffusion model that learns space-group transitions with a Markovian jump process and generates complete crystallographic specifications from a P1 prior.
-
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
MCFlow uses decoupled flow time axes for atom types and crystal structures so a single model handles crystal structure prediction, de novo generation, and atom-type generation.
-
Discovery and recovery of crystalline materials with property-conditioned transformers
Conditioning the attention layers of a crystal-writing transformer on continuous property values enables XRD-based structure recovery and targeted generation of photovoltaic candidates.
-
MiAD: Mirage Atom Diffusion for De Novo Crystal Generation
Mirage infusion lets crystal diffusion models vary atom counts during generation and raises the S.U.N. rate on MP-20 to 8.2%.
-
FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
Combining self-conditioning, fake atoms, and late-stage geometry distortion lets a compact flow-matching model generate nearly always valid 3D drug-like molecules and match training-data chemistry better than existing...
-
Dis-GEN: Disordered crystal structure generation
Dis-GEN learns to represent and generate disordered inorganic crystal structures with partial atomic occupancy and vacancies while preserving crystallographic symmetry.
-
Nature Language Model: Deciphering the Language of Nature for Scientific Discovery
A single sequence-based model, pretrained across molecules, proteins, materials, nucleotides and text, outperforms specialist models on several generation tasks and enables cross-domain design.
-
Open Materials Generation with Stochastic Interpolants
By tuning stochastic interpolants for periodic crystals and coupling them with discrete flow matching, OMatG sets new state-of-the-art results on crystal structure prediction and de novo materials generation.
-
CrystalGRW: Generative Modeling of Crystal Structures with Targeted Properties via Geodesic Random Walks
A Riemannian diffusion model with an equivariant graph network generates crystal structures that sit close to DFT ground states and can be steered toward specified point groups.
-
Generative AI for Crystal Structures: A Review
A structured review of generative models for inorganic crystal structures, covering architectures, representations, datasets, evaluation metrics, and applications without adding new experimental results.
Discussion (0). Continue with ORCID to comment.