Tian Gao

Disentangled Representation Learning for Parametric Partial Differential Equations

Emergent Deceptive Behaviors in Reward-Optimizing LLMs

Scalable Circuit Learning for Interpreting Large Language Models

Towards a Foundation Model Approach for Causal Graph Learning

Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data

Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge

Disentangled Representation Learning for Parametric Partial Differential Equations

Identifying Sub-networks in Neural Networks via Functionally Similar Representations

Benchmarking LLMs on Safety Issues in Scientific Labs