Lili Jiang
Papers
1
Total Citations
3
H-Index
1
About
Lili Jiang is a researcher whose work bridges the frontiers of artificial intelligence and human-computer interaction, with a primary focus on interpretable deep learning. Her key research areas include explainable AI (XAI), computer vision, and contextual reasoning in neural networks. Jiang’s most notable contribution is the development of "Visual Explanations for DNNs with Contextual Importance," a 2021 paper that introduced a novel framework for generating human-understandable visual explanations of deep neural network decisions by incorporating contextual importance—a method that highlights not just which features matter, but why they matter in a given context. This work, while early in its citation trajectory with 3 citations, represents a foundational step toward making AI systems more transparent and trustworthy, particularly in high-stakes applications like medical imaging or autonomous driving. Jiang’s research is characterized by its emphasis on bridging the gap between complex model internals and intuitive user understanding, a challenge that remains central to the responsible deployment of AI. Her ongoing efforts continue to shape how researchers and practitioners approach model interpretability, making her a promising voice in the quest for ethical and accountable artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Visual Explanations for DNNs with Contextual Importance3 citations · 2021