Tongxu Luo

incremental learning (1) neural network optimization (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) parameter efficient fine-tuning (1) mechanistic interpretability (1) role-playing agent (1) causal intervention (1) arithmetic reasoning (1) dialogue agent (1) large language model (1) model growth (1) neuron manipulation (1) multi-character role-playing (1) mlp neuron (1) multi-character role playing (1)