Kai Tong

analytic learning (4) continual learning (4) catastrophic forgetting (3) closed-form solution (3) recursive least squares (2) exemplar-free learning (2) class incremental learning (2) parameter-efficient fine-tuning (1) low-rank adaptation (1) non-iid datum (1) pretrained model (1) generalized class incremental learning (1) large language model (1) dual-stream architecture (1) analytic federated learning (1) single-round aggregation (1) data heterogeneity invariance (1) subspace routing (1) forward-only learning (1) gradient-free training (1)