8 papers
A priori regularity of the reverse heat flow and dimension-dependent complexity of higher-order diffusion samplers
Xixian Wang, Zhongjian Wang
We establish arbitrary-order a priori regularity estimates for the reverse heat flow in the Ornstein--Uhlenbeck setting, that is, for the probability-flow ODE of score-based diffus…
CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction
Kewei Li, Rongying Zhang, Peiyu Yang +4
Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve the underlying mechanisms remai…
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
Kewei Li, Rongying Zhang, Xueli Wang +6
Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduc…
Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation
Kewei Li, Rongying Zhang, Xueli Wang +5
Token aggregation is a common bottleneck in models that map token representations to sample-level predictions, yet most pooling methods operate only in the original token domain. W…
ML-based approach to classification and generation of structured light propagation in turbulent media
Aokun Wang, Anjali Nair, Zhongjian Wang +1
We study the classification task of structured-light beams after propagation through a random turbulent medium. The received speckle patterns are generated by numerical simulation…
Inverse scattering for waveguides in topological insulators
Guillaume Bal, Xixian Wang, Zhongjian Wang
This paper concerns the inverse scattering problem of a topologically non-trivial waveguide separating two-dimensional topological insulators. We consider the specific model of a D…
Wasserstein Bounds for generative diffusion models with Gaussian tail targets
Xixian Wang, Zhongjian Wang
We present an estimate of the Wasserstein distance between the data distribution and the generation of score-based generative models. The sampling complexity with respect to dimens…
classification of FTR symmetric differential operators and obstruction to Anderson localization
Guillaume Bal, Zhongjian Wang
This paper concerns the classification of Fermionic Time-Reversal (FTR) symmetric partial differential Hamiltonians on the Euclidean plane. We consider the setting o…