Lizhong Ding

Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR

Learning for Highly Faithful Explainability

DICT: Uncertainty-Constrained Trustworthiness for Graph Learning

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning

Is It Necessary to Inject Causality into Chain-of-Thought Reasoning?

Rethinking Reward Miscalibration of GRPO in Agentic RL

Distributional Causal Fairness Testing

Generalization Bounds for Kolmogorov-Arnold Networks (KANs) and Enhanced KANs with Lower Lipschitz Complexity

Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration