Shijie Geng

multimodal learning (3) scene graph (2) adversarial learning (1) cross-lingual transfer (1) question answering (1) language grounding (1) multi-modal learning (1) code generation (1) visual grounding (1) adversarial training (1) object localization (1) scene understanding (1) benchmark evaluation (1) low-resource language (1) dynamic graph (1) cross-modal alignment (1) foundation model (1) generative adversarial network (1) vision-language model (1) contrastive learning (1)