Cover Image

Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Xiaoyu, Lu, Jie, Yu, En
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Resilient Contrastive Pre-training under Non-Stationary Drift
by: Yang, Xiaoyu, et al.
Published: (2025)

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
by: Yang, Xiaoyu, et al.
Published: (2025)

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards
by: Yang, Xiaoyu, et al.
Published: (2024)

Understanding the Detrimental Class-level Effects of Data Augmentation
by: Kirichenko, Polina, et al.
Published: (2023)

Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
by: Yang, Xiaoyu, et al.
Published: (2026)

Generating Non-Stationary Textures using Self-Rectification
by: Zhou, Yang, et al.
Published: (2024)

DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
by: Bai, Sikai, et al.
Published: (2024)

MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching
by: Wu, Yen-Siang, et al.
Published: (2025)

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
by: Li, Sheng-Wei, et al.
Published: (2024)

Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
by: Wang, Ziyu, et al.
Published: (2023)

Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
by: Ryu, Sooyoung, et al.
Published: (2026)

Drifting Fields are not Conservative
by: Franz, Leonard T., et al.
Published: (2026)

Knowledge Distillation Based on Transformed Teacher Matching
by: Zheng, Kaixiang, et al.
Published: (2024)

Towards Lifelong Few-Shot Customization of Text-to-Image Diffusion
by: Song, Nan, et al.
Published: (2024)

AerialGo: Walking-through City View Generation from Aerial Perspectives
by: Zhao, Fuqiang, et al.
Published: (2024)

CustomText: Customized Textual Image Generation using Diffusion Models
by: Paliwal, Shubham, et al.
Published: (2024)

Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
by: Yeh, Shih-Ying, et al.
Published: (2023)

Generative Modeling via Drifting
by: Deng, Mingyang, et al.
Published: (2026)

DriftGuard: A Hierarchical Framework for Concept Drift Detection and Remediation in Supply Chain Forecasting
by: Alam, Shahnawaz, et al.
Published: (2026)

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
by: Shaul, Neta, et al.
Published: (2024)

Stable-Drift: A Patient-Aware Latent Drift Replay Method for Stabilizing Representations in Continual Learning
by: Theofilou, Paraskevi-Antonia, et al.
Published: (2025)

Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization
by: Tasyurek, Sumeyye Meryem, et al.
Published: (2025)

Prompt Customization for Continual Learning
by: Dai, Yong, et al.
Published: (2024)

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
by: Shi, Jiang-Xin, et al.
Published: (2023)

Application of Disentanglement to Map Registration Problem
by: Song, Hae Jin, et al.
Published: (2024)

Disentanglement with Factor Quantized Variational Autoencoders
by: Baykal, Gulcin, et al.
Published: (2024)

Drifting Preference Optimization for One-Step Generative Models
by: Jiang, Zhou, et al.
Published: (2026)

Contrast-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
by: Lv, Song-Lin, et al.
Published: (2025)

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning
by: Nai, Ruiqian, et al.
Published: (2024)

Disentangling Polysemantic Channels in Convolutional Neural Networks
by: Hesse, Robin, et al.
Published: (2025)

Disentangled Representation Learning with Transmitted Information Bottleneck
by: Dang, Zhuohang, et al.
Published: (2023)

Disentanglement-Based Equivariant Learning for Compositional VQA
by: Du, Zhou, et al.
Published: (2026)

Disentangled Representation Learning with the Gromov-Monge Gap
by: Uscidda, Théo, et al.
Published: (2024)

Disentangling representations of retinal images with generative models
by: Müller, Sarah, et al.
Published: (2024)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
by: Bian, Jieming, et al.
Published: (2024)

DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
by: Zhou, Zhi, et al.
Published: (2024)

Boosting Adversarial Transferability via Ensemble Non-Attention
by: Zou, Yipeng, et al.
Published: (2025)

Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent
by: Doldo, Philip, et al.
Published: (2025)

PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation
by: Shang, Chikai, et al.
Published: (2025)

Closed-Loop Unsupervised Representation Disentanglement with $β$-VAE Distillation and Diffusion Probabilistic Feedback
by: Jin, Xin, et al.
Published: (2024)