Cover Image

Unlocking [CLS] Features for Continual Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yildirim, Murat Onur, Yildirim, Elif Ceren Gok, Vanschoren, Joaquin
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

Continual Learning on a Data Diet
by: Yildirim, Elif Ceren Gok, et al.
Published: (2024)

Unlocking [CLS] Features for Continual Post-Training
by: Onur Yildirim, Murat, et al.
Published: (2025)

AdaCL:Adaptive Continual Learning
by: Yildirim, Elif Ceren Gok, et al.
Published: (2023)

Self-Regulated Neurogenesis for Online Data-Incremental Learning
by: Yildirim, Murat Onur, et al.
Published: (2024)

Pruned Adaptation Modules: A Simple yet Strong Baseline for Continual Foundation Models
by: Yildirim, Elif Ceren Gok, et al.
Published: (2026)

Automated Machine Learning for Unsupervised Tabular Tasks
by: Singh, Prabhant, et al.
Published: (2025)

CLAMS: A System for Zero-Shot Model Selection for Clustering
by: Singh, Prabhant, et al.
Published: (2024)

Unsqueeze [CLS] Bottleneck to Learn Rich Representations
by: Su, Qing, et al.
Published: (2024)

Learning to Learn without Forgetting using Attention
by: Vettoruzzo, Anna, et al.
Published: (2024)

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs
by: Lappe, Alexander, et al.
Published: (2025)

When are Lemons Purple? The Concept Association Bias of Vision-Language Models
by: Yamada, Yutaro, et al.
Published: (2022)

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
by: Golan, Shelly, et al.
Published: (2026)

Unlocking Compositional Generalization in Continual Few-Shot Learning
by: Nguyen-Lam, Phu-Quy, et al.
Published: (2026)

Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10
by: Yasar, Umut Onur
Published: (2026)

Training Feature Attribution for Vision Models
by: Bacha, Aziz, et al.
Published: (2025)

Retrospective Feature Estimation for Continual Learning
by: Nguyen, Nghia D., et al.
Published: (2024)

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
by: Amini, Sajjad, et al.
Published: (2024)

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
by: Bhalla, Usha, et al.
Published: (2023)

PTQ4SAM: Post-Training Quantization for Segment Anything
by: Lv, Chengtao, et al.
Published: (2024)

PTQ4VM: Post-Training Quantization for Visual Mamba
by: Cho, Younghyun, et al.
Published: (2024)

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
by: Hoang, Dung Anh, et al.
Published: (2026)

MetaAug: Meta-Data Augmentation for Post-Training Quantization
by: Pham, Cuong, et al.
Published: (2024)

COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
by: Zhang, Aozhong, et al.
Published: (2024)

Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
by: Shin, Juncheol, et al.
Published: (2025)

Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
by: Sanga, Prabhav, et al.
Published: (2025)

Confounder-Free Continual Learning via Recursive Feature Normalization
by: Shah, Yash, et al.
Published: (2025)

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
by: Liu, Xuewen, et al.
Published: (2024)

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
by: Hess, Timm, et al.
Published: (2023)

Continual Learning with Pre-Trained Models: A Survey
by: Zhou, Da-Wei, et al.
Published: (2024)

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
by: Bergmeister, Andreas, et al.
Published: (2026)

EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
by: Gordon, Ofir, et al.
Published: (2023)

ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training
by: Colussi, Marco, et al.
Published: (2024)

Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
by: Zhou, Zhongyi, et al.
Published: (2025)

Feature-based Graph Attention Networks Improve Online Continual Learning
by: Sim, Adjovi, et al.
Published: (2025)

Adaptive Retention & Correction: Test-Time Training for Continual Learning
by: Chen, Haoran, et al.
Published: (2024)

Optical Diffusion Models for Image Generation
by: Oguz, Ilker, et al.
Published: (2024)

Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
by: Xu, Jiawen, et al.
Published: (2025)

CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
by: Pandey, Sankalp, et al.
Published: (2025)

ER-FSL: Experience Replay with Feature Subspace Learning for Online Continual Learning
by: Lin, Huiwei
Published: (2024)

PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
by: Sun, Hai-Long, et al.
Published: (2023)