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

Zhanxing Zhu

3 indexed papers

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

Publications per year

3
26

Top categories

AI×2ML×1Crypto×1

Frequent co-authors

Yue Cheng2×
Jiajun Zhang2×
Xiaohui Gao2×
Weiwei Xing2×
Zheng Wang2×
Bochen Lyu1×

Research Timeline

2026
Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and beneficial learning signals for LLMs.

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and beneficial learning signals for LLMs.

When Autoregressive Consistency Hurts Safety Alignment

The paper argues that shallow safety alignment in LLMs is due to autoregressive consistency, a mechanism that allows small harmful inputs to redirect the model's generation to unsafe outputs, necessitating adversarial safety training.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentJun 2, 2026

When Autoregressive Consistency Hurts Safety Alignment

Bochen Lyu, Yiyang Jia, Xiaohao Cai, Zhanxing Zhu

The paper argues that shallow safety alignment in LLMs is due to autoregressive consistency, a mechanism that allows small harmful inputs to redirect the model's generation to unsafe outputs, necessit…

View →
cs.AIRecentMay 27, 2026

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing +2 more

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

View →
cs.AIRecentMay 27, 2026

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing +2 more

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

View →