arXiv AI
Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 18
Geometry of Forgetting: Representation Flux in Continual Learning
arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.
arXiv Machine Learning
Jul 30
The Art of Not Forgetting A Local Learning Architecture for Continual Learning
arXiv:2607. 26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?
arXiv AI
3d ago
Drift-adaptive Representation Preservation for Domain-Incremental Learning
The paper proposes a drift‑adaptive method for Domain‑Incremental Learning that tracks representation drift for each past domain‑class pair. By measuring how much a concept’s current representation deviates from a fixed anchor, the method assigns stronger preservation to high‑drift pairs and down‑weights highly drifted domains during prototype construction. Experiments on DomainNet, Office‑Home, CORe50, and CDDB‑Hard show that this approach maintains a strong accuracy‑forgetting balance while using less training memory and the smallest storage compared to other methods.
arXiv AI
Aug 25
TASSO: TAsk-Specific Subspace Optimization for Continual Learning of Vision-Language Models
arXiv:2608.21487v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) exhibit strong zero-shot capabilities, making them an attractive solution for continual learning across diverse tasks....
arXiv Machine Learning
Oct 5
Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models
The paper introduces a Fisher-guided submodular data selection method for continual pre‑training of large language models, addressing the forgetting problem that arises when a target‑domain corpus overwrites pretrained knowledge. By decomposing candidate gradients into anchor and frontier components and optimizing a log‑determinant submodular objective, the method selects data that both improves target‑domain performance and limits forgetting. Experiments on TinyLlama‑1.1B and Llama‑3.1‑8B show that the selector achieves superior adaptation and forgetting control while using ten times fewer tokens than traditional replay strategies.
arXiv Computation and Language
Oct 8
A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks
arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...