Skip to content
AI News HubLIVE
Original source2 min read

Spectral Feedback for Test-Time Alignment of Protein Diffusion Models

Summary

arXiv:2609.30456v1 Announce Type: new Abstract: Reward maximization alignment methods for discrete diffusion models have primarily focused on steering the reverse process, either by influencing token logits or by selecting favorable sequences at intermediate steps. These approaches largely treat inference as a unidirectional process, lacking mechanisms for revisiting undesirable token selections. We introduce Spectral Feedback, an algorithm that selects edit-positions in a feedback loop, allowing the model to iteratively correct its own generations. This approach leverages the mask structure of discrete diffusion models by re-masking and re-sampling tokens, analogous to image editing methods that reintroduce noisy latents and re-run the reverse process. While prior alignment methods focus…

SourcearXiv AIAuthor: Shai Dickman, Mert Cemri, Landon Butler, Kannan Ramchandran
Spectral Feedback for Test-Time Alignment of Protein Diffusion Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 24 Sep 2026]

Title:Spectral Feedback for Test-Time Alignment of Protein Diffusion Models

View a PDF of the paper titled Spectral Feedback for Test-Time Alignment of Protein Diffusion Models, by Shai Dickman and 3 other authors

View PDF HTML (experimental)

Abstract:Reward maximization alignment methods for discrete diffusion models have primarily focused on steering the reverse process, either by influencing token logits or by selecting favorable sequences at intermediate steps. These approaches largely treat inference as a unidirectional process, lacking mechanisms for revisiting undesirable token selections. We introduce Spectral Feedback, an algorithm that selects edit-positions in a feedback loop, allowing the model to iteratively correct its own generations. This approach leverages the mask structure of discrete diffusion models by re-masking and re-sampling tokens, analogous to image editing methods that reintroduce noisy latents and re-run the reverse process. While prior alignment methods focus on what token labels to assign to maximize a target reward, we instead treat which tokens to revisit as the central alignment problem. Selecting edit-positions is challenging because edit effects are interdependent: the impact of modifying one token depends on which others are edited simultaneously. We define an edit-set as a set of token positions to re-mask and re-sample. Motivated by prior work on sparse interactions in biological systems, we find empirically that edit-set value functions for protein inverse folding admit sparse Fourier representations. This structure enables Spectral Feedback to efficiently learn and optimize the value functions for edit-position selection. Spectral Feedback is model-agnostic and can be applied to pretrained, test-time aligned, and fine-tuned diffusion models. For all of these models, the algorithm improves alignment performance without modifying the underlying generative process. Applied to inverse folding with a protein stability reward oracle, it achieves a 32.3% increase in stable proteins for a pretrained model, 24.8% for Best-of-10, and 5.8% for a state-of-the-art RL fine-tuned diffusion model.

Comments: Neurips 2026

Subjects:

Artificial Intelligence (cs.AI)

ACM classes: I.2.1; I.2.8

Cite as: arXiv:2609.30456 [cs.AI]

(or arXiv:2609.30456v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.30456

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Shai Dickman [view email] [v1] Thu, 24 Sep 2026 18:49:51 UTC (12,041 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Spectral Feedback for Test-Time Alignment of Protein Diffusion Models, by Shai Dickman and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.30456v1 Announce Type: new Abstract: Reward maximization alignment methods for discrete diffusion models have primarily focused on steering the reverse process, either…

Highlights and analysis are generated automatically and may contain errors. Check the original source.