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

Shu Wu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2NLP×2Crypto×1

Frequent co-authors

Liuji Chen1×
Dianxing Tang1×
Xing Shi1×
Dingshuo Chen1×
Qiang Liu1×
Liang Wang1×

Research Timeline

2026
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

This paper analyzes the limitations of Counterfactual Knowledge Training (CFT) for LLM unlearning, identifying knowledge conflict and hallucination spillover as major pitfalls that hinder its effectiveness.

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation quality and robustness, especially under low step budgets.

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

Liuji Chen, Dianxing Tang, Xing Shi, Dingshuo Chen +3 more

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

View →
cs.CLcs.AIRecentMay 31, 2026

DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs

Longxuan Yu, Yunshu Wu, Yu Fu, Siheng Xiong +4 more

The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation q…

View →
cs.CLcs.CRRecentMay 26, 2026

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

Xiaotian Ye, Xiaohan Wang, Mengqi Zhang, Shu Wu

This paper analyzes the limitations of Counterfactual Knowledge Training (CFT) for LLM unlearning, identifying knowledge conflict and hallucination spillover as major pitfalls that hinder its effectiv…

View →