Online kernel regression equals offline regression with shifted targets; correcting the targets lets online learning match offline performance and outperform true targets in continual image classification.
Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
HoReN achieves stable sequential editing of 50K facts in LLMs by combining a normalized Hopfield codebook with angular retrieval and attractor dynamics.
FLAME is an MoE architecture using modality-specific routers and low-rank compression of expert knowledge to support efficient continual multimodal multi-task learning while reducing catastrophic forgetting.
Muon-OGD integrates Muon-style spectral-norm geometry with orthogonal gradient constraints to improve the stability-plasticity trade-off during sequential LLM adaptation.
citing papers explorer
-
Characterizing and Correcting Effective Target Shift in Online Learning
Online kernel regression equals offline regression with shifted targets; correcting the targets lets online learning match offline performance and outperform true targets in continual image classification.
-
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
-
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
HoReN achieves stable sequential editing of 50K facts in LLMs by combining a normalized Hopfield codebook with angular retrieval and attractor dynamics.
-
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
FLAME is an MoE architecture using modality-specific routers and low-rank compression of expert knowledge to support efficient continual multimodal multi-task learning while reducing catastrophic forgetting.
-
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Muon-OGD integrates Muon-style spectral-norm geometry with orthogonal gradient constraints to improve the stability-plasticity trade-off during sequential LLM adaptation.