- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 3(+1)
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The main contribution of Uni² is a joint VAE–diffusion training strategy for biomolecular binder design on the UniMoMo backbone. This strategy replaces the frozen latent interface of two-stage training, allowing diffusion gradients to update the encoder alongside reconstruction objectives. The reported experiments on peptides, antibody CDRs, and pocket-conditioned small molecules support improvements in several primary metrics or aggregate scores.
Critical strengths
-
The method addresses the mismatch between reconstruction-oriented representations and latent generative modeling through a simple joint objective applicable across multiple all-atom binder-design tasks.
-
The method incorporates generative feedback into representation learning, thereby allowing latent representations to adapt to the generative objective. Consistent with this adaptation, latent-distribution analyses indicate improved alignment between generated latents and the encoder’s aggregated posterior.
Critical weaknesses
-
Limited coverage of recent baselines, particularly for antibody design. Beyond UniMoMo, the antibody comparisons in Table 2 rely mainly on methods from 2022–2024, leaving competitiveness against more recent antibody/CDR design approaches unclear. Comparisons should prioritize recent methods that support the same task. Selected broader approaches, such as BoltzGen [1], PXDesign [2], RFdiffusion3 [3], and Proteina-Complexa [4], would also be informative where their tasks and conditioning are compatible.
-
The mechanism underlying the training gains needs further clarification. The shared-backbone comparison and gradient-routing ablations provide useful evidence, but improvements in the fully detached variant indicate that the shared training schedule also contributes to the gains. Meanwhile, Figure 2 and Table 6 support improved latent alignment but do not independently establish improved representation learnability. A clearer explanation connecting the training schedule, diffusion feedback, and latent-space changes to the observed generation gains would strengthen the mechanistic interpretation.
-
The connection between latent alignment and decoded structural quality remains undercharacterized. Reconstruction fidelity, component-wise validity failures, and sensitivity to latent perturbations or iterative decoding are insufficiently analyzed.Table 7 reports lower PB-valid fractions for antibody and small-molecule reconstructions, leaving the relationship between improved latent alignment and decoded structural validity unresolved.
[1] Hannes Stark, Felix Faltings, MinGyu Choi, et al. BoltzGen: Toward Universal Binder Design. bioRxiv preprint, 2025.
[2] Protenix Team, Milong Ren, Jinyuan Sun, et al. PXDesign: Fast, Modular, and Accurate De Novo Design of Protein Binders. bioRxiv preprint, 2025.
[3] Jasper Butcher, Rohith Krishna, Raktim Mitra, et al. De novo Design of All-atom Biomolecular Interactions with RFdiffusion3. bioRxiv preprint, 2025.
[4] Kieran Didi, Zuobai Zhang, Guoqing Zhou, et al. Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute. In International Conference on Learning Representations (ICLR), 2026.
Questions for authors
-
What methodological advances distinguish this approach from existing end-to-end VAE–flow/score models, particularly regarding gradient routing and training stability?
-
How competitive is the method against recent task-compatible baselines under matched data, conditioning, and inference budgets?
-
How do the latent-distribution changes in Figure 2 and Table 6 translate into reconstruction fidelity, decoded geometry, and physical validity, and how sensitive are these effects to the decoder?
6 comments
W3. Latent alignment, reconstruction fidelity, and decoded structural quality
To make the link between reconstruction and generation explicit, we added the following analyses (new Appendix L).
A. Reconstruction fidelity. Reconstruction of the test set by the two-stage VAE (UniMoMo) and by the jointly trained Uni² encoder and decoder. JSD compares the distribution of reconstructed geometry (backbone and side-chain dihedrals for peptides and antibodies, bond lengths and bond angles for small molecules) with that of the ground truth. PB-valid is the PoseBusters-valid fraction of reconstructions.
| Modality | Metric | UniMoMo VAE | Uni² |
|---|---|---|---|
| Peptide | JSD_bb ↓ | 0.166 | 0.164 |
| JSD_sc ↓ | 0.190 | 0.195 | |
| PB-valid ↑ | 0.570 | 0.591 | |
| Antibody | JSD_bb ↓ | 0.229 | 0.227 |
| JSD_sc ↓ | 0.289 | 0.286 | |
| PB-valid ↑ | 0.450 | 0.417 | |
| Small molecule | JSD_BL ↓ | 0.348 | 0.374 |
| JSD_BA ↓ | 0.585 | 0.587 | |
| PB-valid ↑ | 0.570 | 0.530 |
Joint training leaves reconstruction fidelity essentially unchanged: the geometric JSD differs by at most 0.005 for peptides and antibodies and by at most 0.026 for small molecules, and PB-valid of reconstructions improves for peptides. Since generation quality is higher in Uni² (main paper), the gain in generation does not come from a better autoencoder but from a better-aligned latent space.
B. Sensitivity to latent perturbation. We add Gaussian noise (standard deviation σ = 0.1, 0.25, 0.5 in standardized units) to the latent before decoding, and measure the geometric JSD of the decoded structures against the ground truth (lower is better).
| σ | Model | Pep JSD_bb | Pep JSD_sc | Ab JSD_bb | Ab JSD_sc | Mol JSD_BL | Mol JSD_BA |
|---|---|---|---|---|---|---|---|
| 0.1 | UniMoMo | 0.334 | 0.272 | 0.477 | 0.391 | 0.541 | 0.684 |
| Uni² | 0.355 | 0.291 | 0.494 | 0.399 | 0.553 | 0.693 | |
| 0.25 | UniMoMo | 0.499 | 0.301 | 0.673 | 0.365 | 0.610 | 0.686 |
| Uni² | 0.555 | 0.337 | 0.694 | 0.383 | 0.629 | 0.705 | |
| 0.5 | UniMoMo | 0.675 | 0.345 | 0.697 | 0.424 | 0.626 | 0.673 |
| Uni² | 0.666 | 0.368 | 0.682 | 0.438 | 0.641 | 0.707 |
Adding noise degrades the reconstruction of both models, and the two-stage VAE and Uni² behave similarly: at any noise level their JSD differs by at most 0.06 (by 0.02 or less in 12 of 18 entries), and the rise from σ = 0.1 to 0.5 differs by at most 0.03. The decoder of Uni² therefore reacts to latent noise in a similar way, with a slightly higher JSD in 16 of 18 entries (Appendix L, Table 24).
C. Sensitivity to the number of reconstruction iterations. The decoder reconstructs the structure by N rounds of iterative refinement (N = 10 by default). We vary N for the Uni² decoder and measure the geometric JSD of the reconstructions on the test set (lower is better); the N = 10 row is the Uni² result in the table of part A.
| N | Pep JSD_bb | Pep JSD_sc | Ab JSD_bb | Ab JSD_sc | Mol JSD_BL | Mol JSD_BA |
|---|---|---|---|---|---|---|
| 1 | 0.286 | 0.350 | 0.326 | 0.431 | 0.724 | 0.730 |
| 3 | 0.199 | 0.246 | 0.262 | 0.349 | 0.567 | 0.666 |
| 5 | 0.190 | 0.230 | 0.257 | 0.335 | 0.491 | 0.655 |
| 10 | 0.164 | 0.195 | 0.227 | 0.286 | 0.374 | 0.587 |
JSD decreases monotonically with N for every modality and metric. Most of the gain comes from the first three iterations for peptides and antibodies (for example, peptide JSD_bb falls from 0.286 to 0.199), and further iterations keep refining the geometry, which is why we use N = 10 (Appendix L, Table 25).
D. Alignment versus decoded quality. We use the seven unified-training runs of the KL sweep (Appendix I, peptides). For each run we compute the standardized Sliced W1 (SW1) between generated and posterior latents, which measures alignment, and the JSD_bb and JSD_sc of the generated structures, which measure decoded structure quality (Appendix L, Table 26; Figure 8).
| KL multiplier | 10^-3 | 10^-2 | 10^-1.5 | 10^-1 | 10^-0.5 | 10^0.5 | 10 |
|---|---|---|---|---|---|---|---|
| SW1 | 0.0257 | 0.0216 | 0.0317 | 0.0405 | 0.0533 | 0.0776 | 0.1045 |
| JSD_bb | 0.175 | 0.175 | 0.177 | 0.179 | 0.180 | 0.166 | 0.160 |
| JSD_sc | 0.203 | 0.200 | 0.199 | 0.208 | 0.202 | 0.195 | 0.192 |
A linear fit of each JSD against SW1 (see Figure 8 in Appendix L, part D, of the revised paper) gives r = -0.827 and R^2 = 0.684 for JSD_bb, and r = -0.724 and R^2 = 0.524 for JSD_sc. A lower SW1 (better alignment) therefore comes with a higher JSD (worse decoded structure), so alignment and decoded structure quality are negatively correlated, and keeping them balanced is a trade-off.
Q1. Methodological differences from existing end-to-end VAE and flow/score models
Uni² differs from existing end-to-end VAE and flow/score models in three ways.
- Joint training from scratch. Some end-to-end models, such as LSGM [5], first pretrain the VAE and only then train it jointly with the diffusion model, so the latent space is already formed before the diffusion loss acts on it. In Uni², the autoencoder and the denoiser are randomly initialized and optimized together from the first step, so the diffusion loss shapes the latent space throughout training.
- Gradient flow through two latent channels. Uni² has an equivariant geometric latent z_x and an invariant content latent z_h, and the diffusion gradient flows through each channel separately (w/o grad h, w/o grad x, w/o grad h-x).
- Stable training. Existing end-to-end VAE and flow/score models are often unstable: the latent space has no fixed anchor and can drift, and the score-based objective grows without bound at small noise levels, so they rely on extra stabilizers or a pretrained VAE. Uni² avoids both issues. The KL term keeps the latent close to a standard Gaussian, and the epsilon-prediction objective has the same scale at every noise level, so Uni² trains stably from scratch without extra stabilizers. We show this in Appendix F, and the training curves confirm it: the drift of the latent decays while the denoising loss decreases smoothly throughout training (Figure 2, panels (a) and (d) in the paper).
Q2. Competitiveness under matched data, conditioning and inference budgets
Matched data. The four recent antibody baselines (PXDesign, BoltzGen, RFdiffusion3 and Proteina-Complexa) are large-scale pretrained models with their own, larger training data, so we report them as reference points that are matched in evaluation but not in training data. All other antibody baselines in Table 2 are trained and tested on the same dataset as Uni².
Matched conditioning. All antibody baselines in Table 2, including the four recent models, are evaluated on exactly the same test complexes, the same designed region and the same antigen and framework conditioning as Uni².
Matched inference budget. Every antibody method generates the same number of samples per target (n = 100), and no reranking or filtering is applied to any method. The accuracy metrics (AAR, L-RMSD, IMP) and the rationality metrics (clash, JSD) of all antibody models are reported at n = 1, 10 and 100 in Table 2 of the paper.
Result. Even though it is trained only on the shared dataset, Uni² reaches the highest IMP at n=100 (68.33% versus 48.93% for the best of the four), the lowest Clash_in and Clash_out, and the best JSD_sc in Table 2. BoltzGen, RFdiffusion3 and Proteina-Complexa reach a lower RMSD, consistent with their larger models and training data, whereas Uni² covers peptides, antibodies and small molecules with one model.
Q3. From latent alignment to reconstruction and decoded geometry
See W3. Experiment A gives reconstruction fidelity, and experiments B and C measure sensitivity to latent perturbation and to the number of decoding iterations. Experiment D relates latent alignment to decoded structure quality across KL strengths.
References
[1] Hannes Stark, Felix Faltings, MinGyu Choi, et al. BoltzGen: Toward Universal Binder Design. bioRxiv, 2025.
[2] Protenix Team, Milong Ren, Jinyuan Sun, et al. PXDesign: Fast, Modular, and Accurate De Novo Design of Protein Binders. bioRxiv, 2025.
[3] Jasper Butcher, Rohith Krishna, Raktim Mitra, et al. De novo Design of All-atom Biomolecular Interactions with RFdiffusion3. bioRxiv, 2025.
[4] Kieran Didi, Zuobai Zhang, Guoqing Zhou, et al. Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute. ICLR, 2026.
[5] Arash Vahdat, Karsten Kreis, Jan Kautz. Score-based Generative Modeling in Latent Space. NeurIPS, 2021.
We thank the reviewer for the thoughtful comments. Blow is our responses point by point. All new text and experiments are included in the revised PDF and marked in blue.
W1. Comparison with recent antibody and binder design models
We added BoltzGen [1], PXDesign [2], RFdiffusion3 [3] and Proteina-Complexa [4] on antibody design, using the same test complexes and the same number of candidates n as in Table 2. Results are below (AAR and IMP in %; clash in %; RMSD in Å; L-RMSD is the binder RMSD).
Where Uni² stands. Uni² is one model for peptides, antibodies and small molecules, and it is competitive with these recent general-purpose binder design models. At n=100 it has the highest IMP (68.33% versus 48.93% for the best baseline), the lowest clash rates (0.12% and 0.03%), and the best side-chain JSD (0.217). Its AAR (50.32%) is close to BoltzGen and Proteina-Complexa (52.71% and 52.62%) and higher than RFdiffusion3 and PXDesign. Its L-RMSD (0.85) is lower than PXDesign (2.50), while BoltzGen, RFdiffusion3 and Proteina-Complexa (0.46, 0.52, 0.77) are lower. These models were designed for a broad range of targets; our contribution is a training recipe that improves a given model (Uni² over UniMoMo here), so it is complementary to scaling up those models.
W2. Mechanism: how the training schedule, diffusion feedback and latent changes lead to the gains
We separate the gain into three links, each supported by a measurement.
The shared schedule removes most of the sequential-training mismatch. The fully detached variant (w/o grad h-x) keeps one schedule but blocks the diffusion gradient. On peptides it already improves L-RMSD from 1.48 to 0.90, ΔG from -28.72 to -32.61, IMP from 29.03% to 36.56%, and Clash_out from 0.94% to 0.16% (Section 5).
Diffusion feedback adds a further gain on top of the schedule. Moving from the detached variant to the full model improves every row shown below.