Fangming Liu

large language model (5) catastrophic forgetting (2) model compression (2) knowledge editing (2) reinforcement learning (1) continual learning (1) post-training quantization (1) text classification (1) contrastive learning (1) fact verification (1) knowledge distillation (1) policy learning (1) in-context learning (1) question answering (1) toxicity detection (1) multimodal learning (1) adversarial robustness (1) fine-grained classification (1) model merging (1) representation learning (1)