Metraipolis › archive › dc_d6245ceeee9f
Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion — arXiv:2609.31222
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31222
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:13:11.671Z
- SHA-256 of the archived text
16a7fbffd27b272c851ab20506f8b96b6d95c2d54c1b4001db8fb2eb45e38b61- Stable URL of this page
https://metraipolis.com/documento/dc_d6245ceeee9f
How to cite
Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion — arXiv:2609.31222 — arXiv (en), https://arxiv.org/abs/2609.31222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d6245ceeee9f (Metraipolis archive dc_d6245ceeee9f, sha256 16a7fbffd27b272c851ab20506f8b96b6d95c2d54c1b4001db8fb2eb45e38b61)
BibTeX
@misc{dcd6245ceeee9f,
title = {Budgeted Quotient-Residual Guidance for Frozen Pocket-Conditioned Molecular Diffusion — arXiv:2609.31222},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d6245ceeee9f; sha256 16a7fbffd27b272c851ab20506f8b96b6d95c2d54c1b4001db8fb2eb45e38b61},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pocket-conditioned molecular diffusion updates ambient atom coordinates, but many lead-optimization objectives are expressed on quotient features such as distances, contacts, and anchored substructures. We introduce budgeted quotient-residual guidance (QRG), an inference-time correction that makes these quotient objectives active without retraining the molecular generator. QRG lifts quotient covectors to metric-horizontal ambient directions and delivers them through a trust budget set by the frozen sampler's own step norm: quotient geometry chooses the direction, while sampler motion bounds the scale. We derive the horizontal lift, closed-form sampler-budget update, KL/kinetic interpretation around a frozen reverse step, equivariance conditions, and a product-budget split for budget-capped section and residual controls. Controlled quotient tasks confirm that sampler-relative delivery activates signals that raw local quotient gradients leave dormant. On frozen TargetDiff backbones, official seed-0 CBGBench ligand-generation/editing sweeps show practical quality-runtime gains: Local-QRG improves validity from 0.815 to 0.864 on fragment growing, 0.664 to 0.707 on scaffold hopping, and 0.681 to 0.712 on linker design, while PredNext-QRG improves fragment/scaffold and remains near-neutral on linker. Novelty remains 1.000 and diversity is preserved in the matched multi-seed molecular slice, giving task-dependent improvements without sampler retraining or backbone modification. Overall, QRG provides a lightweight route to quotient-aware inference for frozen molecular samplers with explicit runtime accounting. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.31222 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:43:06.740Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).