Author

Zhengyang Shan

h-index 3 View on Semantic Scholar

We have 3 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 Apr 2026

Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs

Results show that proxy-based empirical gain achieves strong ranking agreement with proxy-defined realized utility and substantially outperforms row-count and token-count baselines in the tested setting, while the prototype provides a controlled sanity check of the valuation pipeline and its sensitivity to duplication-...

Ming-Hui Xu, Qi-Meng Luo, Kun Li et al. · arXiv.org · 1 citation

#artificial intelligence Preprint Sep 2026

UNBIND: UNlearning By INference-time Directional Steering for Code LLMs

Multilingual and related-code evaluations further show effective forgetting with limited impact on useful programming capabilities, supporting UNBIND as a practical approach to selective code unlearning.

Zhengyang Shan, Jia-Yu Xin, Yan-Jun Lin et al. · 0 citations

Preprint Aug 2026

OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents

OBLIVION, a controlled benchmark and defense harness for revoked-skill resurrection, and results support workflow-level evaluation beyond checking explicit skill entries support workflow-level evaluation beyond checking explicit skill entries.

Zhengyang Shan, Xuancheng Qian, Jiayu Xin et al. · 0 citations