arXiv AI
Jul 13
Interference and Retention in Continual Learning
arXiv:2607. 09202v1 Announce Type: cross Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation.
When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
Related stories
arXiv AI
Jul 22
Soft-TransFormers for Continual Learning
arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.
arXiv Machine Learning
1d ago
Muon Can Outperform Dedicated Continual Learning Methods
arXiv:2609.24678v1 Announce Type: new Abstract: Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated past...
arXiv Machine Learning
Sep 1
One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning
arXiv:2608.31096v1 Announce Type: cross Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...
arXiv AI
Jul 20
PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning
arXiv:2601. 13020v2 Announce Type: replace-cross Abstract: Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities.
arXiv Machine Learning
Aug 28
Unifying Detection and Adaptation in Task-Free Continual Learning
The paper introduces FiUni, a Fisher-guided unified framework that performs batch-level task detection and parameter-efficient continual adaptation for large language models. By exploiting orthogonality in the Fisher information matrix’s Kronecker-Factored Approximate Curvature subspaces, FiUni constructs frozen subspaces to guide low-rank adaptation and matches incoming batch windows to historical subspaces. This approach allows the model to decide whether to reuse, expand, or create new subspaces, balancing knowledge sharing and task isolation while achieving competitive performance with fewer trainable parameters.
arXiv Machine Learning
5d ago
A Noise Optimum in Rehearsal-Free Continual Learning: Isolation, Mechanism, and Scope
The paper demonstrates that adding stochastic noise to a consolidation rule can improve a neural network’s retention of earlier tasks up to an optimal level, after which performance degrades, forming an inverted‑U relationship. Through simulations on related‑task continual‑learning benchmarks, the authors isolate the conditions that produce this optimum, showing it requires coherent restoration toward consolidated weights and is linked to the noise variance. The study further maps the scope of the effect, noting it depends on shared task structure and diminishes with more tasks, while a single‑seed hardware demonstration is referenced elsewhere.
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 19
Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning
arXiv:2606. 20431v1 Announce Type: new Abstract: Continual learning (CL) systems often forget previously acquired knowledge, yet the mechanisms driving forgetting remain hard to isolate in practice because real datasets entangle many factors.
arXiv AI
Jul 23
An Isotropy-Preserving Spectral Cap for Muon: Theory and Three Case Studies
arXiv:2607. 19771v1 Announce Type: cross Abstract: Muon and related matrix-sign optimizers are increasingly used to pre-train large language models, but their effect on the internal geometry of individual weight matrices is not well understood.
arXiv AI
Jun 17
PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
arXiv:2602. 03846v2 Announce Type: replace-cross Abstract: We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable.
arXiv Machine Learning
Jul 28
Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning
arXiv:2607. 23837v1 Announce Type: new Abstract: Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forgetting.