Author

Zehao Liu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models

Across three models and three post-training methods on competition math benchmarks, it is found that leakage is real, causal, and substantial: behavioral and representational analyses reveal shifts toward Think, and bidirectional interventions support a substantial causal contribution of thinking leakage.

Ze-Hao Liu, Vasant Honavar · 0 citations

Preprint Aug 2026

PAC-Bayes Beyond Parameter Space: Behavioral Equivalence, Z-Information, and Exact Complexity Decomposition

PAC-Bayes theory provides generalization guarantees by controlling the Kullback--Leibler (KL) divergence between posterior and prior distributions over a chosen hypothesis representation. However, predictive risk depends only on the predictive behavior induced by a hypothesis, not on the particular internal realization...

Vasant Honavar, Satish Kumar Keshri, Neil Ashtekar et al. · 0 citations