Jianghong Ma

multimodal learning (2) contrastive learning (1) image generation (1) self-attention mechanism (1) collaborative filtering (1) visual question answering (1) chain-of-thought reasoning (1) sentiment classification (1) image editing (1) graph embedding (1) diffusion model (1) sequential recommendation (1) vision-language model (1) counterfactual reasoning (1) satellite imagery (1) recommender system (1) backdoor adjustment (1) semantic understanding (1) part-level editing (1) large language model (1)