Data geometry makes time identifiable from noisy interpolants at rate O(1/sqrt(d-k)), rendering the time-blindness gap asymptotically negligible relative to coupling variance.
The geometry of noise: Why diffusion models don’t need noise conditioning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
Condition-wise Sinkhorn drifting is presented as a one-shot conditional channel simulator using a Sinkhorn objective trained via barycentric velocities and detached particle regression, outperforming other one-shot variants on conditional checks but trailing diffusion on SER.
Timestep embeddings are redundant in diffusion models under certain conditions, with time-agnostic variants matching or exceeding conditioned models on FID, precision, and recall for CelebA and CIFAR-10.
citing papers explorer
-
What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
Data geometry makes time identifiable from noisy interpolants at rate O(1/sqrt(d-k)), rendering the time-blindness gap asymptotically negligible relative to coupling variance.
-
Generative Pseudo-Force Fields for Molecular Generation
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
-
Condition-Wise Sinkhorn Drifting for One-Shot Learned Channel Simulation
Condition-wise Sinkhorn drifting is presented as a one-shot conditional channel simulator using a Sinkhorn objective trained via barycentric velocities and detached particle regression, outperforming other one-shot variants on conditional checks but trailing diffusion on SER.
-
On the Redundancy of Timestep Embeddings in Diffusion Models
Timestep embeddings are redundant in diffusion models under certain conditions, with time-agnostic variants matching or exceeding conditioned models on FID, precision, and recall for CelebA and CIFAR-10.