HyLoVQA: Dynamic Hypernetwork-Generated Low-Rank Adaptation for Continual Visual Question Answering

ArXi:2605.22035v1 Announce Type: cross Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge. Most prior methods adapt by updating a largely shared parameter set. This often leads to cross-level task interference, hindering accurate adaptation to the current task and object. To address this limitation, we propose HyLoVQA. It maintains a drift-resilient memory bank of anchors. The bank s the content of visual objects and textual tasks, and they are updated using current input features.