- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces a method for symmetry aware crystal generation called GEODE (Generative Equivariant Orbit Diffusion Engine), building on other symmetry aware methods like SGFM (Punt et al, 2025), SGEquiDiff (Chang et al, 2025), and DynaCris (Jin et al, 2026). GEODE generates a crystal in two parts: first, a VAE is trained to generate a crystal template consisting of the space group and a list of Wyckoff orbits . Given a template, PyXtal is used to generate an initial crystal consistent with the template. At this point, GEODE undertakes a single joint diffusion in i) the lattice parameters, ii) the atom types, and iii) the atom positions (expressed in a cartesian coordinates instead of fractional), conditioned on the template to arrive at the final generated crystal. This diffusion preserves the symmetry template throughout to guarantee that the generated crystal is still consistent with the template. The authors then provide an evaluation of de novo generation on the MP-20 and the larger Alex-MP-20 datasets, where GEODE provides generally improved metrics over other symmetry aware methods, especially in the mSUN rate (metastable, unique, and novel structures). The authors then give several ablation studies showing the various effects of filtering templates, various diffusion settings (e.g. cartesian vs fractional diffusion), among others.
Critical strengths
-The Paper propose a new symmetry aware method for de novo crystal generation that does a good job of decoupling templates specifying the symmetry and the properties to be diffused. This allows for a simple filtering method that drastically increases quality metrics (in particular mSUN) by getting rid of improbable templates for a specific problem.
-The Paper provides comprehensive evaluations demonstrating the effectiveness of their method along with ablations to demonstrate future directions of study, with property guidance perhaps being the most interesting for real world applications.
Critical weaknesses
-While the mSUN metric was better than other symmetry aware structures, the rest of the metrics seem to be marginal improvements (at best) over existing symmetry aware methods. Furthermore, while GEODE does close the gap versus symmetry agnostic methods, I found it interesting that overall they still seem to dominate the metrics. Thus, the question of how useful GEODE is for real world chemistry remains uncertain.
-The diffusion is computationally expensive as currently laid out, requiring 1000 reverse steps per sample, with each step entailing a full pass through the network. This limits throughput, and as the authors point out, some other method like flow matching might be preferred.
Questions for authors
-While the mSUN was reported for all methods, what about the SUN rate? In general, why is the definition of "metastable" useful here? Is it the fact that these crystals are more likely to become stable after relaxation?
-From reading this, it seems like GEODE gives evidence towards doing as much joint diffusion as possible to increase expressivity. Would it ever be possible to also incorporate diffusion into the Wyckoff sites themselves (or even the spacegroups too), giving the model further flexibility?
-In Section 5.6, I didn't understand if there was anything special to GEODE that made it particularly special to property steering (apart from easy template filtering). In principle, it seems like most other symmetry aware crystal generative models could also do this fine-tuning process to learn to generate crystals with a certain material property.
4 comments
(Part 2 of 3)
Q1a. What are the SUN rates, and how should they be interpreted alongside mSUN?
We now report SUN alongside mSUN in all tables. GEODE achieves the highest SUN rate on both datasets, with 2.12% on MP-20 for filtered, pre-relaxed GEODE and 1.32% on Alex-MP-20 for unfiltered, pre-relaxed GEODE.
| Model | Valid (%) | Unique (%) | Novel (%) | Metastable (%) | SUN (%) | mSUN (%) | (eV/atom) | RMSD (Å) |
|---|---|---|---|---|---|---|---|---|
| MP-20 | ||||||||
| Symmetry-agnostic | ||||||||
| Crystalite* | 95.80 | 53.20 | 1.50 | 22.60 | ||||
| Chemeleon 2 RL | 95.20 | 88.10 | 71.60 | 39.80 | 0.04 | 21.20 | 0.16 | 0.42 |
| MCFlow* | 52.20 | 49.30 | 0.70 | 18.90 | 0.10 | 0.17 | ||
| MatterGen* | 95.70 | 95.10 | 70.50 | 33.40 | 0.24 | 15.00 | 0.18 | 0.39 |
| DiffCSP | 95.70 | 94.80 | 66.20 | 29.80 | 0.12 | 8.50 | 0.28 | 0.59 |
| Symmetry-aware | ||||||||
| SGFM | 95.20 | 93.90 | 42.60 | 45.70 | 0.28 | 7.68 | 0.25 | 0.44 |
| DiffCSP++ | 95.30 | 95.10 | 62.00 | 26.40 | 0.16 | 4.96 | 0.41 | 0.70 |
| SGEquiDiff | 91.90 | 91.30 | 58.20 | 22.70 | 0.08 | 2.92 | 0.53 | 0.90 |
| CrystalFormer | 69.70 | 69.10 | 30.80 | 28.00 | 0.00 | 2.56 | 0.67 | 0.65 |
| WyFormer | 93.70 | 93.30 | 66.20 | 16.50 | 0.08 | 2.40 | 0.49 | 0.77 |
| SymmCD | 73.40 | 73.00 | 47.00 | 18.60 | 0.08 | 2.36 | 0.88 | 0.87 |
| GEODE | 95.80 | 94.90 | 55.80 | 41.90 | 0.62 | 11.92 | 0.20 | 0.42 |
| GEODE* | 95.60 | 94.90 | 54.30 | 43.70 | 1.20 | 16.40 | 0.14 | 0.15 |
| GEODE-filtered* | 96.40 | 95.30 | 38.80 | 0.16 | 0.20 | |||
| Alex-MP-20 | ||||||||
| Chemeleon 2 RL | 93.50 | 67.40 | 0.20 | 0.10 | 0.27 | |||
| Chemeleon 1 | 94.00 | 93.90 | 59.80 | 54.40 | 0.96 | 28.00 | 0.11 | 0.31 |
| CrystaLLM- | 93.40 | 93.20 | 23.90 | 0.32 | 12.48 | 0.09 | 0.19 | |
| GEODE | 95.00 | 54.10 | 57.70 | 1.06 | 25.78 | 0.10 | 0.30 | |
| GEODE* | 95.00 | 52.50 | 61.80 | 29.20 | ||||
| GEODE-filtered* | 94.80 | 94.60 | 64.20 | 61.70 | 1.20 | 36.76 | 0.09 | 0.12 |
Table 1 of the paper with the SUN rate added, 2,500 structures per model. Relaxed before evaluation. Best value per dataset underlined.
An important detail of LeMat-GenBench is that mSUN excludes stable structures. SUN counts unique and novel structures with , while mSUN counts those with eV/atom. In practice, when searching for new materials, the metric of interest would be the combination of both stable and low-energy metastable candidates. On MP-20, filtered, pre-relaxed GEODE gives the highest combined rate (25.92%), followed by pre-relaxed Crystalite (24.10%).
Q1b. Why include metastable structures? Are they expected to become stable after relaxation?
A structure can remain above the hull after relaxation and still be experimentally accessible. Relaxation can bring a structure to a local energy minimum even when another phase, or combination of phases, has a lower energy. Sun et al. found that 50.5% of 29,902 experimentally observed inorganic phases lay above the calculated 0 K hull (Sun et al., Sci. Adv. 2, e1600225, 2016).
There are several reasons for this. Entropy can stabilise a phase at finite temperature, and kinetic barriers can allow a metastable phase to persist (e.g. diamond is metastable above the ground state of graphite). The DFT energies used to train the machine-learned interatomic potentials also carry uncertainties that affect estimated hull distances. Including candidates up to 0.1 eV/atom above the hull therefore lets us retain plausible materials that a strict ground-state criterion would exclude.
(Part 3 of 3)
W2. Does the cost of 1,000 reverse steps limit throughput?
With the same 1,000-step sampler, the optimised implementation now generates 2,500 MP-20 structures in 2.16 h on one Quadro RTX 6000, down from 17.4 h. The corresponding reported times are 6.06 h for MatterGen and 3.5 min for Crystalite. The EquiformerV3 denoiser now accounts for most of GEODE's generation time. Our symmetry-conserving framework is agnostic to the choice of denoiser. Replacing it with Crystalite's would bring the total generation time down significantly. We describe the implementation changes in the general response.
Q2. Could jointly diffusing the Wyckoff sites or even the space group give GEODE more flexibility?
This is an interesting suggestion that we are currently exploring. Allowing the Wyckoff assignments or space group to change during denoising would let GEODE revise its initial symmetry template as the atom types, coordinates and lattice evolve. The difficulty is that changing a symmetry assignment also changes which atomic coordinates can move independently. For example, lowering the space group can split one Wyckoff orbit into several, allowing previously equivalent atoms to move independently. If the symmetry instead increases, those atoms must be brought into positions that are exactly related by the higher symmetry, and their atom types must agree. A joint diffusion process would therefore need to update the discrete symmetry assignment, the atom types and the continuous geometry consistently at each transition. For our subsequent work, we are exploring whether these symmetry changes can be incorporated directly into GEODE's coordinate and lattice diffusion. Whether the added flexibility improves generation quality remains an open question.
DynaCrys explores a simpler version of this problem (arXiv:2608.07401, 2026). It jointly diffuses only the atom types, space group and Wyckoff occupations. The coordinates are generated in a second stage with all three held fixed. This makes the symmetry transitions considerably easier to handle because the model can change the occupied Wyckoff orbits without having to map the free coordinates of the old orbits onto those of the new ones.
Q3. Is property steering specific to GEODE?
We agree that other symmetry-aware models can also be fine-tuned for property-guided generation. CrystalFormer-RL, for example, has been used to target dielectric and band-gap properties (Cao and Wang, arXiv:2504.02367, 2025).
The purpose of Section 5.6 is to show how symmetry control and property guidance can be used together. Restricting GEODE to cubic templates requires no additional training and ensures that the dielectric tensor is isotropic. Property guidance then steers the magnitude of the predicted permittivity towards the target value. We will clarify this distinction in Section 5.6.
Response to the Authors
I thank the authors for their thorough responses to my questions. I also think the performance improvements detailed are significant to the work as the overall pipeline is much more usable at this point. I also think it would be interesting to see how using Crystalite's decoder further improves throughput. In general, I am very optimistic about symmetry-aware approaches to this problem, and feel like they are ultimately the right way to solve this. Thus, I have increased my score as I think this would be a fine paper to accept. I think the only remaining reservation I have is that it's still a bit unclear to me how much these additional architecture changes/joint diffusion really help over the existing symmetry aware approaches.
(Part 1 of 3)
We thank the reviewer for highlighting the value of separating the symmetry template from the generation of the crystal structure, and for their questions about the evaluation and possible extensions.
We agree that some individual metrics, such as validity, improve only slightly. For materials discovery, however, what matters is how often the same candidate is low in energy, unique and novel. Each criterion is relatively easy to satisfy in isolation. A model can generate low-energy structures by reproducing the training set, while random structures can be both unique and novel but are rarely low in energy. Meeting all three criteria simultaneously makes mSUN a more demanding measure of generation quality.
The comparison with SGFM illustrates this point. On MP-20, SGFM generates a higher fraction of metastable structures than unfiltered GEODE (45.7% versus 41.9%), yet GEODE generates substantially more candidates that are simultaneously metastable, unique and novel (11.92% versus 7.68% of all samples). GEODE also more than doubles the SUN rate (0.62% versus 0.28%) and achieves a lower mean energy above the hull (0.20 versus 0.25 eV/atom), before either template filtering or pre-relaxation.
Several symmetry-agnostic models outperform unfiltered GEODE on MP-20, although the ranking depends on the model and metric. After pre-relaxation with a machine-learned interatomic potential, unfiltered GEODE achieves higher SUN and mSUN rates than pre-relaxed MatterGen (1.20% versus 0.24% SUN and 16.40% versus 15.00% mSUN). Crystalite achieves higher rates on both measures (1.50% SUN and 22.60% mSUN).
On Alex-MP-20, Chemeleon 2 achieves the highest mSUN rate after reinforcement learning with rewards for uniqueness, novelty and energy above the hull. This raises its mSUN rate from 11.80% to 62.40%, while its SUN rate falls from 0.56% to 0.20%. GEODE does not use reward fine-tuning, so the Chemeleon 2 base model provides a more direct comparison. Unfiltered GEODE achieves 25.78% mSUN before pre-relaxation and 29.20% afterwards. The pre-relaxed model also achieves the highest SUN rate on this dataset (1.32%).
For real-world materials discovery, we need confidence that generations are realistic suggestions. One aspect of this is that generations should reproduce the kinds of crystal symmetry seen in experiment. LeMat-GenBench's metrics do not capture this aspect of generation quality. This limitation has previously been highlighted in the literature, e.g., Jin et al. introduce the SSUN@τ metric, which additionally requires a non-P1 space group after relaxation, in addition to being valid, unique and stable.
Crucially, only 1.20% of Alex-MP-20 training structures belong to P1, the space group with no symmetry beyond translations. By comparison, 40.00% of MatterGen samples and 95.52% of Chemeleon 2 base samples belong to P1. A search using these models would therefore systematically undersample crystals with nontrivial symmetry. For GEODE the fraction is 0.94%. GEODE also more closely reproduces the full point-group distribution, with a Jensen–Shannon distance of 0.06 from the training set, compared with 0.59 for MatterGen and 0.96 for Chemeleon 2 base.
This matters directly when a real-world application calls for a particular symmetry. In Section 5.6, for example, we search for dielectrics with an isotropic response and a target permittivity. With GEODE (or most other symmetry-aware models), we can restrict generation to cubic templates, which ensures isotropy, and use property guidance to target the desired permittivity. Every generated candidate therefore meets the symmetry requirement before we evaluate its predicted permittivity.