Siwei Chen
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper systematically performs a differential fault analysis (DFA) on the lightweight block cipher Lilliput, demonstrating that it is significantly vulnerable to practical fault attacks even under relaxed adversarial assumptions.
The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distribution towards conciseness and certainty.
Papers
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
Yujie Wang, Siwei Chen, Longzan Luo, Xinyi Liu +3 more
The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…