Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported performance on earlier tasks. We challenge the stronger form of this view. Across controlled continual-learning settings, we find that a significant portion of apparent forgetting can be attributed to interface drift between internal stages rather than permanent erasure of task-relevant computation. We study this phenomenon through a stitched evaluation protocol that combines early computation from a post-update network with late computation from its predecessor, optionally mediated by a compact, task-specific transport key. We describe transport keys at a systems level as compact interface-alignment operators estimated from a small set of paired anchor activations and evaluated through model stitching. On split CIFAR-100 with a ResNet-style network, transport keys recover most of the original Task A performance after sequential training on Task B. On a compact vision transformer, we observe a similar recovery pattern. These results suggest that continual learning may require better mechanisms for indexing and re-accessing latent computations, not only methods that prevent weight change.
University of Bologna（博洛尼亚大学）；University of Pisa（比萨大学）
On-device training for personalized learning is a challenging research problem. Being able to quickly adapt deep prediction models at the edge is necessary to better suit personal user needs. However, adaptation on the edge poses some questions on both the efficiency and sustainability of the learning process and on the ability to work under shifting data distributions. Indeed, naively fine-tuning a prediction model only on the newly available data results in catastrophic forgetting, a sudden erasure of previously acquired knowledge. In this paper, we detail the implementation and deployment o…
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
Practical Continual Forgetting for Pre-trained Vision Models
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（人工智能与机器人中心，香港科学创新研究院，中国科学院）；SenseTime Research（商汤科技研究院）
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）；Huawei（华为）
Imperial College London（帝国理工学院）；Google DeepMind（谷歌DeepMind）
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge. Whereas in a neural network the parameters are typically modelled as scalar values, an individual synapse in the brain comprises a complex network of interacting biochemical components that evolve at different timescales. In this paper, we show that by equipping tabular and deep reinforcement learning agents with a synaptic model t…
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
MPI for Intelligent Systems, Tübingen（马克斯·普朗克智能系统研究所（蒂宾根））；Jinesis Lab, University of Toronto & Vector Institute（Jinesis实验室，多伦多大学与向量研究所）；EuroSafeAI；Hector Foundation（赫克托基金会）；Stanford University（斯坦福大学）；ELLIS Institute Tübingen（ELLIS研究所（蒂宾根））
$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
School of Computer Science and Technology, Xi’an Jiaotong University, China（西安交通大学计算机科学与技术学院）；MOE KLINNS Lab, Xi’an Jiaotong University, China（西安交通大学MOE KLINNS实验室）；Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China（陕西省大数据知识工程重点实验室）
