Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jin Wang

Jin Wang

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×3ML×2Crypto×2Neural Computing×1

Frequent co-authors

Yuwei Miao2×
Gen Li2×
Yunsheng Zeng2×
Xiandong Li2×
Yujin Wang2×
Siyu Chen2×

Research Timeline

2026
ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attacks

The paper introduces ReproMIA, a novel and efficient framework that uses model reprogramming to proactively amplify and detect latent privacy leakage for Membership Inference Attacks (MIAs), significantly outperforming state-of-the-art methods, especially in low False Positive Rate regimes.

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills

SkillScope introduces a graph-based framework to enforce fine-grained least-privilege in LLM Agent Skills, significantly reducing over-privileged actions while maintaining task functionality.

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing methods.

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stability in open-ended QA.

Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds

This paper proposes a learning-based framework, CBA-BO, for solving expensive constrained optimization problems with continuously varying threshold settings by learning a parametric constraint model.

Highlighted terms show continued research focus across papers

Papers

cs.NEcs.AIcs.LGEmpiricalRecentJul 26, 2026

Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds

Jin Wang, Xi Lin, Handing Wang

This paper proposes a learning-based framework, CBA-BO, for solving expensive constrained optimization problems with continuously varying threshold settings by learning a parametric constraint model.

View →
cs.AIRecent
May 27, 2026

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

Yuwei Miao, Gen Li, Yunsheng Zeng, Xiandong Li +7 more

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing m…

View →
cs.AIRecentMay 27, 2026

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

Yunsheng Zeng, Gen Li, Yuwei Miao, Xiandong Li +7 more

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stabil…

View →
cs.CRRecentMay 7, 2026

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills

Jiangrong Wu, Yuhong Nan, Yixi Lin, Huaijin Wang +3 more

SkillScope introduces a graph-based framework to enforce fine-grained least-privilege in LLM Agent Skills, significantly reducing over-privileged actions while maintaining task functionality.

View →
cs.LGcs.CRRecentMar 30, 2026

ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attacks

Chihan Huang, Huaijin Wang, Shuai Wang

The paper introduces ReproMIA, a novel and efficient framework that uses model reprogramming to proactively amplify and detect latent privacy leakage for Membership Inference Attacks (MIAs), significa…

View →