2 papers
cs.LG2026
Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition
Haoren Xu, Guanhua Fang
Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the model behaves as though it…
cs.CV2026
Zero-Shot Chinese Character Recognition via Global-Local Dual-Branch Alignment and Hierarchical Inference
Wei Cao, Hao Xu, Xiaolei Diao
Chinese character categories are extremely large, and unseen characters frequently arise in open-world scenarios, making zero-shot Chinese character recognition an important yet ch…