No article text was recorded for this version.
staged fine-tuning
Version 1 of 189 papers106 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy
- Blog: Improving Representational Continuity via Continued Pretraining
- Blog: Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Blog: Fine-tuning Pre-trained Models for Robustness under Noisy Labels
- Blog: Learning for Expressive Task-Related Sentence Representations
- Blog: Non-Contrastive Self-Supervised Learning for Utterance-Level Information Extraction From Speech
- Blog: A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning
- Blog: Learning to Generalize for Cross-domain QA
- Blog: WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks
- Blog: How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems
- Blog: VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
- Blog: End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021
- Blog: $\mathtt {RE\text{- }Tagger}$: A Light-Weight Real-Estate Image Classifier
- Blog: On the Convergence of Differentially-Private Fine-tuning: To Linearly Probe or to Fully Fine-tune?
- Blog: Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion
- Blog: Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Blog: Few-Shot Learning for Video Object Detection in a Transfer-Learning Scheme
- Blog: lo-fi: distributed fine-tuning without communication
- Blog: UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction
- Blog: Accelerating Heterogeneous Federated Learning with Closed-form Classifiers
- Blog: Automated Detection of Potholes in Pavements using Deep Neural Networks with Fine Tuning and Data Augmentation Techniques
- Blog: FSDN-DETR: Enhancing Fuzzy Systems Adapter with DeNoising Anchor Boxes for Transfer Learning in Small Object Detection
- Blog: Conversion and Implementation of State-of-the-Art Deep Learning Algorithms for the Classification of Diabetic Retinopathy
- Blog: Are Fast Methods Stable in Adversarially Robust Transfer Learning?
- Blog: Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
- Blog: Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
- Blog: Towards Secure Tuning: Mitigating Security Risks Arising from Benign Instruction Fine-Tuning
- Blog: Interpretable Sperm Morphology Classification via Attention-Guided Deep Learning
- Blog: Elastic Neural Networks for Classification
- Blog: Stroke Sequence-Dependent Deep Convolutional Neural Network for Online Handwritten Chinese Character Recognition
- Blog: Speech-FT: A Fine-tuning Strategy for Enhancing Speech Representation Models Without Compromising Generalization Ability
- Blog: GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization
- Blog: Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
- Blog: Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings
- Blog: AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning
- Blog: Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
- Blog: ISDS-NLP at SemEval-2024 Task 10: Transformer based neural networks for emotion recognition in conversations
- Blog: A Second-Order Perspective on Model Compositionality and Incremental Learning
- Blog: Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
- Blog: UZH at PAN-2023: Profiling Cryptocurrency Influencers using Ensemble of Language Models
- Blog: MSnet: A BERT-based Network for Gendered Pronoun Resolution
- Blog: Open Domain Generalization with a Single Network by Regularization Exploiting Pre-trained Features
- Blog: Neural Experts: Mixture of Experts for Implicit Neural Representations
- Blog: Deep neural network training emphasizing central frames
- Blog: Decoupled Finetuning for Domain Generalizable Semantic Segmentation
- Blog: Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generation
- Blog: Meta-HAR: Federated Representation Learning for Human Activity Recognition
- Blog: Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy
- Blog: Idling Neurons, Appropriately Lenient Workload During Fine-Tuning Leads to Better Generalization
- Blog: Novel dual-input stream-based hybrid approach for wheat leaf disease classification using edge-aware features
- Blog: DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
- Blog: Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification
- Blog: Advacheck at GenAI Detection Task 1: AI Detection Powered by Domain-Aware Multi-Tasking
- Blog: Delving into Multimodal Prompting for Fine-grained Visual Classification
- Blog: Multi-task Voice Activated Framework using Self-supervised Learning
- Blog: SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
- Blog: Learning to Generalize for Cross-domain QA
- Blog: Multimodal Emotion Recognition using Transfer Learning from Speaker Recognition and BERT-based models
- Blog: StyleLess layer: Improving robustness for real-world driving
- Blog: Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
Showing 60 of 89 papers.
History & citation
Current · Permanent link
- This direction split from Sequential Linear Probing and Fine-Tuning for Robust Adaptation (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_staged_fine_tuning_6dd8ef20,
title = {staged fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/staged-fine-tuning/rdr_6dd8ef20ce2d4491b624ae61a71bbbf7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_staged_fine_tuning_6dd8ef20_v1,
title = {staged fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/staged-fine-tuning/rdr_6dd8ef20ce2d4491b624ae61a71bbbf7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}