Zihui Song
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×2ML×1
Frequent co-authors
Research Timeline
2026
Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
The paper introduces Expected Value Alignment (EVA), a novel reward modeling procedure that allows continuous scoring of intermediate reasoning steps in formal mathematics verification while maintaining the discrete, textual output format of generative models.
Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context
Soft-NBCE introduces soft entropy-weighted chunk fusion to overcome the semantic fragmentation caused by hard chunk selection in long-context LLMs, significantly improving performance on multi-hop benchmarks.
Highlighted terms show continued research focus across papers
Papers
cs.AIRecentMay 31, 2026
Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification
The paper introduces Expected Value Alignment (EVA), a novel reward modeling procedure that allows continuous scoring of intermediate reasoning steps in formal mathematics verification while maintaini…
View →
cs.LGcs.AIRecentMay 31, 2026