Qianren Wang

large language model (4) model compression (1) domain adaptation (1) text classification (1) question answering (1) model architecture (1) model editing (1) backdoor attack (1) vision-language model (1) mechanistic interpretability (1) token pruning (1) inference efficiency (1) retrieval-augmented generation (1) table-to-text generation (1) parameter editing (1) hierarchical aggregation (1) tree mapreduce (1) hierarchical semantic parsing (1) long-context reasoning (1) performance benchmark (1)