Zechen Li

multi-task learning (2) human activity recognition (2) dialog generation (2) visual question answering (1) question answering (1) multimodal learning (1) multi-modal learning (1) visual reasoning (1) multi-view learning (1) retrieval-augmented generation (1) sensor datum (1) masked token prediction (1) masked language modeling (1) synthetic dataset (1) human mobility (1) dialogue system (1) urban computing (1) large language model (1) urban region embedding (1) point-of-interest datum (1)