Jianhuang Lai

Injecting physics-inspired spatial priors into video MLLMs drastically enhances temporal stability and segmentation accuracy without sacrificing image-level performance.

COSMO redefines source-free domain adaptation by dynamically balancing the influence of source models and vision-language models, achieving unprecedented performance while mitigating source bias.

Achieve state-of-the-art person re-identification with only 20% of the data by explicitly teaching the model to "think" before matching identities.