Explainable Multimodal Agents With Symbolic Representations & Can AI Be Less Biased?

Our junior member Ruotong Liao is an invited speaker at the United Nations "AI for Good"!

With her talk "Perceive, Remember, and Predict: Explainable Multimodal Agents with Symbolic Representations," Ruotong Liao will participate in the online event "Explainable Multimodal Agents with Symbolic Representations & Can AI be less biased?" hosted by the United Nations AI for Good.

AI for Good is the United Nations' leading platform for artificial intelligence for sustainable development, with the goal of identifying trustworthy AI applications, building competencies and standards, and promoting AI governance for sustainable development.

Ruotong Liao's talk will explore how the integration of temporal reasoning and symbolic knowledge about evolving events enables LLMs to make structured, interpretable, and context-sensitive predictions. Ruotong Liao will present work aimed at developing explainable multimodal agents capable of perceiving, storing, predicting, and justifying their conclusions over time.