paper-with-me

홈 › Papers

Adaptive Subspace Projection for Generative Personalization

2026-05-08 · Van-Anh Nguyen, Anh Tuan Bui, Tamas Abraham, Junae Kim, Amardeep Kaur, Rollin Omari, Thuy-Trang Vu, Dinh Phung arxiv

Generative personalization often suffers from the semantic collapsing problem (SCP), where a learned personalized concept overpowers the rest of the text prompt, causing the model to ignore important contextual details. To address this, we first analyze the underlying cause, revealing that the semantic drift responsible for SCP is not random but is concentrated within a specific low-dimensional subspace. We also discover that the personalization process perturbs the embedding of the original base concept, making it an unstable reference point. Based on these insights, we introduce Test-time Embedding Adjustment with Adaptive Subspace Projection (AdaptSP), a training-free method that uses the stable, pre-trained embedding as an anchor. AdaptSP isolates the semantic drift and projects it onto the identified subspace, performing a precise adjustment that mitigates SCP while maintaining the subject identity. Our experiments show that this targeted approach significantly improves prompt fidelity and contextual alignment.

📄 PDF Abstract BibTeX arXiv:2605.07257

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Enhanced Random Subspace Local Projections for High-Dimensional Time Series Analysis

2026-03-08 · Eman Khalid, Moimma Ali Khan, Zarmeena Ali, Abdullah Illyas 외 arxiv

High-dimensional time series forecasting suffers from severe overfitting when the number of predictors exceeds available observations, making standard local projection methods unstable and unreliable. We propose an enhan…

Time Series ForecastingTime Series Analysis

Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method

2022-04-09 · Zhijian Li, Jack Xin

We propose an adaptive projection-gradient descent-shrinkage-splitting method (APGDSSM) to integrate penalty based channel pruning into quantization-aware training (QAT). APGDSSM concurrently searches weights in both the…

Quantization

Wasserstein Projection Pursuit of Non-Gaussian Signals

2023-02-24 · Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar

We consider the general dimensionality reduction problem of locating in a high-dimensional data cloud, a $k$-dimensional non-Gaussian subspace of interesting features. We use a projection pursuit approach -- we search fo…

Dimensionality Reduction

NBNet: Noise Basis Learning for Image Denoising with Subspace Projection

2020-12-30 · CVPR 2021 1 · Shen Cheng, Yuzhi Wang, Haibin Huang, Donghao Liu 외

In this paper, we introduce NBNet, a novel framework for image denoising. Unlike previous works, we propose to tackle this challenging problem from a new perspective: noise reduction by image-adaptive projection. Specifi…

DenoisingImage DenoisingSSIM

FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning

2023-11-30 · Lingzhi Gao, Zexi Li, Yang Lu, Chao Wu

Personalized federated learning (pFL) enables collaborative training among multiple clients to enhance the capability of customized local models. In pFL, clients may have heterogeneous (also known as non-IID) data, which…

Federated LearningPersonalized Federated Learning