No article text was recorded for this version.
catastrophic forgetting (catastrophic forgetting in fine-tuning)
Version 1 of 1728 papers771 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Model selection, adaptation, and combination for transfer learning in wind and photovoltaic power forecasts
- Blog: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
- Blog: Rethinking the Domain Gap in Near-infrared Face Recognition
- Blog: Probing Pretrained Models of Source Code
- Blog: Is in-domain data beneficial in transfer learning for landmarks detection in x-ray images?
- Blog: Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering
- Blog: Gradient Estimation for Unseen Domain Risk Minimization with Pre-Trained Models
- Blog: Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval
- Blog: Do Satellite Tasks Need Special Pretraining?
- Blog: Multimodal Pretraining of Medical Time Series and Notes
- Blog: TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers
- Blog: How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
- Blog: ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning
- Blog: Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
- Blog: BERTnesia: Investigating the capture and forgetting of knowledge in BERT
- Blog: XTab: Cross-table Pretraining for Tabular Transformers
- Blog: SMILES-Inspired Transfer Learning for Quantum Operators in Generative Quantum Eigensolver
- Blog: DNN Explanation for Safety Analysis: an Empirical Evaluation of Clustering-based Approaches
- Blog: ERM++: An Improved Baseline for Domain Generalization
- Blog: Simplifying Models with Unlabeled Output Data
- Blog: How to Boost Face Recognition with StyleGAN?
- Blog: Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
- Blog: On consequences of finetuning on data with highly discriminative features
- Blog: Transfer without Forgetting
- Blog: Better Fine-Tuning by Reducing Representational Collapse
- Blog: Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
- Blog: Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems
- Blog: Universal Domain Adaptation from Foundation Models
- Blog: TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
- Blog: Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
- Blog: Robust Synthetic-to-Real Transfer for Stereo Matching
- Blog: Large Convolutional Model Tuning via Filter Subspace
- Blog: Towards Open-Vocabulary Scene Graph Generation with Prompt-Based Finetuning
- Blog: Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
- Blog: Is forgetting less a good inductive bias for forward transfer?
- Blog: Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models
- Blog: The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
- Blog: Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models
- Blog: Taming Latent Diffusion Models to See in the Dark
- Blog: LPT++: Efficient Training on Mixture of Long-tailed Experts
- Blog: Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
- Blog: How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
- Blog: Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
- Blog: Self-Tuning for Data-Efficient Deep Learning
- Blog: LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
- Blog: Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study
- Blog: MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
- Blog: Universal Prompt Tuning for Graph Neural Networks
- Blog: Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation
- Blog: MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
- Blog: Learning More Universal Representations for Transfer-Learning
- Blog: Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
- Blog: On Surgical Fine-tuning for Language Encoders
- Blog: Self-supervised similarity models based on well-logging data
- Blog: LoFiT: Localized Fine-tuning on LLM Representations
- Blog: Constrained Diffusion Models via Dual Training
- Blog: Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation
- Blog: Pay Attention to Small Weights
- Blog: Representation Consolidation for Training Expert Students
- Blog: Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens
Showing 60 of 728 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_catastrophic_forgetting_catastrophic_for_801e5c65,
title = {catastrophic forgetting (catastrophic forgetting in fine-tuning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/catastrophic-forgetting-catastrophic-forgetting-in-fine-tuning/rdr_801e5c65bbb4441c8edb2948f5907fd5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_catastrophic_forgetting_catastrophic_for_801e5c65_v1,
title = {catastrophic forgetting (catastrophic forgetting in fine-tuning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/catastrophic-forgetting-catastrophic-forgetting-in-fine-tuning/rdr_801e5c65bbb4441c8edb2948f5907fd5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}