Software

Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
Unsupervised anomaly detection from the mismatch between a flow matching model’s learned velocity and the direct velocity toward a test image, giving pixel-wise heatmaps and image-level scores.
PDF Project
Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
Personalized Federated Hierarchical Gaussian Processes for Privacy-Preserving Modeling of Heterogeneous Distributed Systems
arXiv preprint, September 2026.
Xianjian Xie, Hao Yan
PDF
Publication Home
Below is the full list of publications with Hao Yan as author or co-author, grouped by year (synced from HaoYan.bib). For grants, awards, and service, see the curriculum vitae PDF alongside my faculty page.
Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping
arXiv preprint, September 2026.
PDF
Structurally Separated DAG Learning with Multi-Scale Normalized Closure
Accepted to NeurIPS 2026.
Shuai Feng, Hao Yan
Adaptive Sampling for Automated Post-Disaster Rapid Damage Assessment via Level-Set Cost-Aware Bayesian Optimization
Accepted to SDM 2026.
PDF Project
Aleatoric-Aware Posterior Regularized Bayesian Neural Networks for Incorporating Domain Knowledge: Addressing Epistemic and Aleatoric Uncertainties
Accepted to INFORMS Journal on Data Science.
Bayesian Entropy Neural Networks for physics-aware prediction
Bayesian entropy neural networks for physics-aware prediction in engineering systems.
Project DOI
D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
A unified, threshold-free differentiable convex-shape prior based on quasi-concavity of the segmentation mask function. Zero-, first-, and second-order characterizations yield a midpoint convexification algorithm and compact convolutional losses that integrate seamlessly with modern segmentation networks via the proposed Convex Gradient Projection Module (CGPM). Accepted to CVPR 2026 as a Highlight.
PDF Code Project Poster
D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
Flow-matching distributional RL with source-consistent Bellman-coupled paths and shared-noise coupling between current and successor return flows. A lambda-parameterized control variate reduces bootstrap variance while preserving Gaussian source and Bellman endpoint geometry. Strong distributional fidelity on toy MRPs and competitive offline RL on 38 OGBench and D4RL tasks. Accepted to ICML 2026 as a regular presentation.
PDF Code Project
Path-Coupled Bellman Flows for Distributional Reinforcement Learning