arXiv AI
Aug 13
Representation Finetuning for Continual Learning
arXiv:2603. 11201v3 Announce Type: replace-cross Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams.
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.
Related stories
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.
arXiv AI
Sep 28
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
The paper introduces EoupCT, a framework that estimates and orthogonalizes unknown pre‑training gradients to mitigate catastrophic forgetting during continual fine‑tuning of large language models. It generates pseudo data most susceptible to forgetting using a learnable soft prompt with Gumbel‑Softmax, then jointly optimizes model parameters and the prompt via a first‑order Pareto optimizer to enforce orthogonality between new task updates and the estimated gradients. Experiments on multiple LLMs show that EoupCT preserves both task‑specific performance and the models’ inherent general‑purpose knowledge.
arXiv Statistics ML
Oct 2
ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs
ChainLoRA is a replay‑free continual learning framework for large language models that merges task vectors while preserving geometry. It uses chain‑updated training with a one‑sided orthogonality proxy to keep historical state and regularization overhead constant, and applies post‑stream adaptive SVD merging with Procrustes adaptation to separate shared and task‑specific components. Experiments demonstrate state‑of‑the‑art performance on Large and SuperNI benchmarks and competitive results on Standard CL, approaching the scores of replay‑based methods.
arXiv AI
Oct 16
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
CRAFT is a continual learning framework that freezes model weights and learns low‑rank interventions on hidden representations to mitigate catastrophic forgetting. Tasks that are similar share an intervention, determined by how they change the model’s output distribution, and a KL penalty keeps new tasks close to existing behavior. The approach also allows task identification at test time without explicit labels and shows improved performance and reduced forgetting across benchmarks compared to LoRA‑based methods.
arXiv AI
Jun 8
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
arXiv:2606. 07500v1 Announce Type: cross Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge.
arXiv Machine Learning
Oct 8
Continual Learning without Continual Training
arXiv:2610.10379v1 Announce Type: new Abstract: Continual learning requires models to adapt to new domains and new classes while retaining prior knowledge. Many existing methods rely on continued opt...
arXiv AI
Aug 7
CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
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 Machine Learning
Jul 3
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
arXiv:2602. 00722v2 Announce Type: replace Abstract: Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge.
arXiv Machine Learning
Sep 10
Continual Learning Mechanisms Compose for Long-Horizon Memorization
arXiv:2609.06986v1 Announce Type: new Abstract: Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we i...
arXiv Machine Learning
Aug 18
Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning
arXiv:2608. 16345v1 Announce Type: new Abstract: Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation to new tasks.