arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
Trust Region Continual Learning as an Implicit Meta-Learner
The paper introduces Trust Region Continual Learning, a hybrid approach that blends generative replay with a Fisher-metric trust region constraint to address catastrophic forgetting in sequential task learning. It demonstrates that, under local approximations, the update can be interpreted as a single-step Model-Agnostic Meta-Learning (MAML) process, where replay provides an old-task gradient and the Fisher penalty shapes curvature. Experiments on task-incremental diffusion image generation and continual diffusion-policy control show that this method achieves superior final performance, better retention, and faster early-task recovery compared to EWC, replay, and other continual meta-learning baselines.
Related stories
arXiv AI
Jun 3
Re-Evaluating Continual Learning with Few-Shot Adaptation
arXiv:2606. 03843v1 Announce Type: cross Abstract: Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks.
arXiv Machine Learning
Jul 10
When Does Continual Learning Require Learning
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv Machine Learning
Aug 18
Metaplasticity as adaptive gradient preconditioning for incremental learning
arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.
arXiv Machine Learning
Oct 23
Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability
The paper introduces an algorithmic stability framework to analyze catastrophic forgetting in continual learning using SGD, without assuming a specific model architecture. It decomposes forgetting into intra‑task and cross‑task generalization gaps plus empirical forgetting, and derives bounds for different learning‑rate schedules. Experiments on Split CIFAR‑100 and Split MiniImageNet illustrate the theoretical insights.
arXiv AI
Jul 8
To Retain or to Adapt? Generalizing Continual Learning
arXiv:2607. 05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting.
arXiv Machine Learning
Jun 9
Theoretical Foundations of Continual Learning via Drift-Plus-Penalty
arXiv:2606. 08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch.
arXiv Machine Learning
Aug 13
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv AI
5d ago
Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning
The paper introduces Fisher-Shaped EWC (FS‑EWC), a replay‑free continual learning method that extends Elastic Weight Consolidation by controlling Fisher sensitivity over a neighborhood of future updates. FS‑EWC minimizes the worst‑case empirical Fisher information trace during task learning, favoring solutions robust to bounded parameter displacement, and uses trajectory‑based model merging to construct the retained solution from multiple optimization states. Experiments on several benchmarks demonstrate that FS‑EWC outperforms standard EWC, achieving a better stability–plasticity balance and higher tolerance to parameter drift.
arXiv Machine Learning
Jul 20
Rethinking Transfer in Continual Learning: A Replay-Based Realisation
arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.
arXiv Computer Vision
Oct 15
Data-Free Continual Learning for World Action Model with Rectified Generative Replay
arXiv:2610.18038v2 Announce Type: replace-cross Abstract: World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned...
Hugging Face Trending Papers
6d ago
Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning
The paper introduces Fisher-Shaped EWC (FS‑EWC), a method that extends Elastic Weight Consolidation by controlling Fisher sensitivity over a neighborhood of potential future updates. FS‑EWC minimizes the worst‑case empirical Fisher information trace during task learning, favoring solutions less sensitive to bounded future displacement, and uses trajectory‑based model merging to construct the retained solution. Experiments on multiple benchmarks show that FS‑EWC outperforms standard EWC, achieving a better stability–plasticity balance and greater tolerance to parameter drift.