Online Continual Learning

Online continual learning studies how models can learn from data as it arrives, often in a single pass and without known task boundaries, while retaining useful information from the past. Common approaches use replay buffers or structured memories, constrain updates with regularization or parameter-efficient adapters, expand model capacity, or detect distribution shifts to trigger targeted updates. Researchers evaluate these methods on streaming vision and language tasks, time-series drift, robotics, and resource-constrained devices, measuring accuracy, forgetting, transfer, memory, and compute. A central challenge is balancing adaptation to new or recurring patterns against retention, while ensuring results hold under realistic streams and do not depend on hidden assumptions such as task labels or pretrained features.