Skip to content

Author

Junchen Wan

We have 2 of 14 papers

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.

#artificial intelligence Preprint Oct 2026

MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning

GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correctness with rollout generation entropy. Correctness determines the sign of an add...

Ji-Hao Huang, Guang-Jia Chai, Zhi-Rui Chen et al. · 0 citations
Preprint Aug 2026

CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship

CompanionBench, an interactive bilingual benchmark to ground both its scenarios and a trained user simulator in de-identified real-world data, and is the first companion benchmark to ground both its scenarios and a trained user simulator in de-identified real-world data.

Yaopei Liu, Guang-Jia Chai, Yu-Ming Huang et al. · 2 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.