activity
20242026
collaborators

6 papers

cs.CV2026

Improving Classifier-Free Guidance of Flow Matching via Manifold Projection

Jian-Feng Cai, Haixia Liu, Zhengyi Su +1

Classifier-free guidance (CFG) is a widely used technique for controllable generation in diffusion and flow-based models. Despite its empirical success, CFG relies on a heuristic l…

eess.IV2026

MAP-based Problem-Agnostic diffusion model for Inverse Problems

Pingping Tao, Haixia Liu, Jing Su

Diffusion models have indeed shown great promise in solving inverse problems in image processing. In this paper, we propose a novel, problem-agnostic diffusion model called the max…

cs.LG2026

BlockRR: A Unified Framework of RR-type Algorithms for Label Differential Privacy

Haixia Liu, Yi Ding

In this paper, we introduce BlockRR, a novel and unified randomized-response mechanism for label differential privacy. This framework generalizes existed RR-type mechanisms as spec…

stat.ML2026

RPWithPrior: Label Differential Privacy in Regression

Haixia Liu, Ruifan Huang

With the wide application of machine learning techniques in practice, privacy preservation has gained increasing attention. Protecting user privacy with minimal accuracy loss is a…

cs.LG2025

Fairness via Independence: A (Conditional) Distance Covariance Framework

Ruifan Huang, Haixia Liu

We explore fairness from a statistical perspective by selectively utilizing either conditional distance covariance or distance covariance statistics as measures to assess the indep…

cs.LG2024

The Exploration of Neural Collapse under Imbalanced Data

Haixia Liu

Neural collapse, a newly identified characteristic, describes a property of solutions during model training. In this paper, we explore neural collapse in the context of imbalanced…