collaborators

22 papers

cs.LG2026

Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation

Kun Fang, Qinghua Tao, Mingzhen He +6

The paper proposes a kernel PCA based method for out-of-distribution detection that learns a discriminative non-linear subspace using a newly designed Cosine-Gaussian kernel and in…

cs.CV2026

Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model

Kun Fang, Zuopeng Yang, Haibo Hu +3

The paper introduces DDR, a method that evaluates the difference between an input image and its diffusion‑model reconstruction using the classifier’s deep feature and logit represe…

cs.LG2026

CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

Gengyu Zhang, Haiyin Ran, Zhengbao He +4

As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently…

cs.CV2026

Stochastic Optimal Control Sampling for Diffusion Inverse Problems

Jie Zhang, Youmei Qiu, Hanling Tian +3

Benefiting from the strong ability to capture data distributions, diffusion models have become powerful tools for solving image inverse problems. The key is to controllably steer t…

cs.LG2026

SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector

Jingyuan Zhang, Yucheng Bai, Peixi Wen +6

Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off b…

cs.LG2026

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

Zhengbao He, Ruiqi Ding, Zhehao Huang +3

Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapt…