Metraipolis › archive › dc_19143147acee
OOD Generalization as a Bifurcation Problem — arXiv:2609.33562
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33562
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:01:32.680Z
- SHA-256 of the archived text
22d10ff66f008a9e35405f650cac12926ddcb6cb1ef8cb444a100f2ee89d5da9- Stable URL of this page
https://metraipolis.com/documento/dc_19143147acee
How to cite
OOD Generalization as a Bifurcation Problem — arXiv:2609.33562 — arXiv (en), https://arxiv.org/abs/2609.33562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19143147acee (Metraipolis archive dc_19143147acee, sha256 22d10ff66f008a9e35405f650cac12926ddcb6cb1ef8cb444a100f2ee89d5da9)
BibTeX
@misc{dc19143147acee,
title = {OOD Generalization as a Bifurcation Problem — arXiv:2609.33562},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33562},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19143147acee; sha256 22d10ff66f008a9e35405f650cac12926ddcb6cb1ef8cb444a100f2ee89d5da9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Systematic out-of-distribution (OOD) generation remains a critical bottleneck for continuous-time generative models. While standard joint classifier-free guidance (CFG) routinely fails to synthesize unobserved concept combinations, exact decomposed scoring generalizes robustly at the cost of severe computational overhead. In this work, we reveal that compositional binding is not a uniform process but a highly localized phase transition. We identify the semantic bifurcation window - the precise temporal interval where joint and decomposed vector fields meaningfully diverge. Exploiting this dynamic, we propose surgical guidance, a hybrid sampling strategy that restricts exact multi-pass scoring strictly to this critical window. On an OOD bi-digit MNIST testbed, surgical guidance achieves state-of-the-art compositional fidelity at a fraction of the inference cost, yielding a +5.3% absolute improvement in pairwise accuracy over the joint baseline by intervening during just the first 15% of the diffusion trajectory. Furthermore, our empirical analysis uncovers a fundamental topological divide: diffusion models (SDEs) force conceptual resolution immediately at peak noise, whereas Conditional Flow Matching (ODEs) delays structural binding until intermediate features emerge, establishing a new temporal framework for accelerating large-scale generative decoding. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.33562 — 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 2026-10-07T20:29:02.689Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).