Author

Yi-Dan Lin

h-index 2 View on Semantic Scholar

We have 2 of 5 papers

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 Preprint Nov 2025

MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS

MAS-Shield is proposed, a secure and efficient defense framework designed with a coarse-to-fine filtering pipeline that achieves a 92.5\% recovery rate against diverse adversarial scenarios and reduces defense latency by over 70\% compared to existing methods.

Kai-Xiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov et al. · 2 citations

Preprint Aug 2026

Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents

This work introduces Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory that is trained with evidence-level supervision and rationale-conditioned representation distillation and achieves strong answer quality while maintaining low online latency.

Yi-Dan Lin, Kai-Xiang Wang, Jiong Lou et al. · 1 citation