Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Xiaoyu, Lu, Jie, Yu, En
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Generative Modeling via Drifting
por: Deng, Mingyang, et al.
Publicado: (2026)

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

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

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

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

Prompt Customization for Continual Learning
por: Dai, Yong, et al.
Publicado: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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