Jiale Liu

multimodal learning (2) transformer architecture (1) link prediction (1) uncertainty modeling (1) visual question answering (1) iterative refinement (1) node classification (1) vision-language model (1) positional encoding (1) retrieval-augmented generation (1) robustness evaluation (1) spatial reasoning (1) multimodal reasoning (1) image-text alignment (1) generative optimization (1) scalable optimization (1) signed graph (1) agent system (1) link sign prediction (1) llm agent (1)