Ge Wang

The paper introduces AgentSchool, an advanced LLM-powered multi-agent simulator that models learning as state transitions to provide a robust, ethically viable testbed for educational research and pedagogical reform.

HypothesisMed introduces an inference-time pipeline for biomedical question answering that improves model reliability and structured output generation by fusing multiple model outputs and diagnosing the answer space.

CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superior generalization.