ReA-Bench: Benchmarking Responsible Agent Auditingwith Zipeng Ye, Shenyu Dai, Yong Xie, Kun Wang +41 versionW_x8p3tq6ev1 · current
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning ModelsShuqiang Wang, Wei Cao, Jiaqi Weng et al.0 citations2605.13338v22026Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), PMLR 306, 2026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM SafetyJunxiao Yang, Haoran Liu, Jinzhe Tu et al.0 citations2604.12710v22026arXiv
A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion ModelsQinqin He, Jiaqi Weng, Jialing Tao et al.0 citations2509.21008v12025arXiv
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation FrameworkJiaqi Weng, Han Zheng, Hanyu Zhang et al.0 citations2509.18127v32025Findings of the Association for Computational Linguistics: ACL 2026, pages 18916-18935 (2026)
Measurement Models For Sailboats Price vs. Features And Regional AreasJiaqi Weng, Chunlin Feng, Yihan Shao1 citation2309.14994v12023arXiv
Prediction Model For Wordle Game Results With High RobustnessJiaqi Weng, Chunlin Feng0 citations2309.14250v12023arXiv