Author

Ziyang Chen

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Apr 2026

PolicyLong: Towards On-Policy Context Extension

PolicyLong is proposed, shifting data construction towards a dynamic on-policy paradigm, by iteratively re-executing data screening (entropy computation, retrieval, and verification) using the current model, which ensures the training distribution tracks evolving capabilities, yielding an emergent self-curriculum.

Junlong Jia, Jiangnan Zhou, Ziyang Chen et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Aug 2026

LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails

LongGuard is presented, a framework that evaluates, mechanistically analyzes, and mitigates long-context guardrail failure, and proposes two training-free mitigations - Chunked Detection and Attention-Head Sharpening (AHS) - and a deployment protocol that selects configurations by context length and audit side.

Ziyang Chen, Xing Wu, Songlin Hu · 0 citations