Ming Kong

video understanding (2) large language model (2) scene understanding (1) weakly supervised learning (1) multimodal learning (1) 3d vision (1) parameter-efficient learning (1) synthetic data generation (1) multiple instance learning (1) query learning (1) diffusion model (1) mixture of expert (1) vision-language model (1) hallucination mitigation (1) soft prompt (1) hallucination reduction (1) large vision-language model (1) multimodal language model (1) temporal understanding (1) multi-hop reasoning (1)