Zhanxing Zhu
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
ML×1Crypto×1AI×1
Frequent co-authors
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.
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
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