Image de couverture de livre

Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Steele, Brady
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning I.2.6; I.5.1
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SATORIS-N: Spectral Analysis based Traffic Observation Recovery via Informed Subspaces and Nuclear-norm minimization
par: Mohanty, Sampad, et autres
Publié: (2026)

AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark
par: Katakam, Raj Kiran Gupta
Publié: (2026)

Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
par: Dutta, Utsav, et autres
Publié: (2026)

Remaining Useful Life Estimation for Turbofan Engines: A Comparative Study of Classical, CNN, and LSTM Approaches
par: Goel, Astitva, et autres
Publié: (2026)

The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations
par: Bird, George
Publié: (2025)

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
par: Lachapelle, Sébastien, et autres
Publié: (2024)

Mamba base PKD for efficient knowledge compression
par: Medina, José, et autres
Publié: (2025)

ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space
par: Yong, Shim Soon
Publié: (2025)

Feature emergence via margin maximization: case studies in algebraic tasks
par: Morwani, Depen, et autres
Publié: (2023)

Learning to Land Anywhere: Transferable Generative Models for Aircraft Trajectories
par: Larsen, Olav Finne Praesteng, et autres
Publié: (2025)

Contrastive Representation Modeling for Anomaly Detection
par: Lunardi, Willian T., et autres
Publié: (2025)

AdaCap: An Adaptive Contrastive Approach for Small-Data Neural Networks
par: Belucci, Bruno, et autres
Publié: (2025)

Entropy Aware Message Passing in Graph Neural Networks
par: Nazari, Philipp, et autres
Publié: (2024)

Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension
par: Herde, Marek, et autres
Publié: (2024)

Efficient Action-Constrained Reinforcement Learning via Acceptance-Rejection Method and Augmented MDPs
par: Hung, Wei, et autres
Publié: (2025)

Structured Contrastive Learning for Interpretable Latent Representations
par: Shen, Zhengyang, et autres
Publié: (2025)

In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models
par: Gu, Enhao, et autres
Publié: (2025)

Information-Theoretic Quality Metric of Low-Dimensional Embeddings
par: Gutiérrez-Bernal, Sebastián, et autres
Publié: (2025)

Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing
par: Sun, Yuhui, et autres
Publié: (2025)

Emergence of Quantised Representations Isolated to Anisotropic Functions
par: Bird, George
Publié: (2025)

QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization
par: Jiang, Xiantao
Publié: (2026)

Explicit Dropout: Deterministic Regularization for Transformer Architectures
par: Agrawal, Vidhi, et autres
Publié: (2026)

Towards Automated Diagnosis of Inherited Arrhythmias: Combined Arrhythmia Classification Using Lead-Aware Spatial Attention Networks
par: Sigfstead, Sophie, et autres
Publié: (2026)

Massive Redundancy in Gradient Transport Enables Sparse Online Learning
par: Merin, Aur Shalev
Publié: (2026)

Bayesian X-Learner: Calibrated Posterior Inference for Heterogeneous Treatment Effects under Heavy-Tailed Outcomes
par: Uehara, Eichi
Publié: (2026)

DeepDTF: Dual-Branch Transformer Fusion for Multi-Omics Anticancer Drug Response Prediction
par: Zhao, Yuhan, et autres
Publié: (2026)

SeizureFormer: A Transformer Model for IEA-Based Seizure Risk Forecasting
par: Feng, Tianning, et autres
Publié: (2025)

Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection
par: Williamson, Dane, et autres
Publié: (2025)

Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanations
par: Carrow, Stephen, et autres
Publié: (2024)

GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality
par: Liu, Zehao, et autres
Publié: (2025)

Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
par: Zhang, Xu, et autres
Publié: (2025)

Optimizing Inference in Transformer-Based Models: A Multi-Method Benchmark
par: Ho, Siu Hang, et autres
Publié: (2025)

Aggregating Direct and Indirect Neighbors through Graph Linear Transformations
par: Rosenhoover, Marshall, et autres
Publié: (2025)

Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding
par: Hahn, Yannik, et autres
Publié: (2025)

Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
par: Febrinanto, Falih Gozi, et autres
Publié: (2023)

Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels
par: Du, Wenzhang
Publié: (2025)

Augmenting Replay in World Models for Continual Reinforcement Learning
par: Yang, Luke, et autres
Publié: (2024)

Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay
par: Du, Wenzhang
Publié: (2025)

Regularisation in neural networks: a survey and empirical analysis of approaches
par: Opperman, Christiaan P., et autres
Publié: (2026)

Efficient Strategy for Improving Large Language Model (LLM) Capabilities
par: Gutiérrez, Julián Camilo Velandia
Publié: (2025)