2 papers
cs.LG2026
MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning
Xiangjun Shi, Chong Mu, Jinchuan Zhang +3
Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual lear…
cs.LG2026
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Shuaizhi Cheng, Xiang Shi, Zhiwei Zhang +1
Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document c…