Publications

Xinjie Shen 沈鑫杰, Junran Wang, Rongzhe Wei, Pan Li (2026). SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents. arXiv.

PDF Code Project Page Dataset Model

Xinjie Shen 沈鑫杰, Wei Fan, Xudong Guo, Jianhong Tu, Yang Su, Chuqiao Kuang, Yinger Zhang, Dayiheng Liu (2026). Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms. Qwen Technical Report.

PDF Figure Design Notes

Wei Fan, Xinjie Shen 沈鑫杰, Xudong Guo, Jianhong Tu, Yang Su, Yinger Zhang, Lianghao Deng, Fengyu Wang, Baohua Dong, Yangqiu Song, Dayiheng Liu (2026). E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation. arXiv.

Xinjie Shen 沈鑫杰, Rongzhe Wei, Peizhi Niu, Haoyu Wang, Ruihan Wu, Eli Chien, Bo Li, Pin-Yu Chen, Pan Li (2026). One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue. ICML AIWILD 2026.

PDF Code Project Page

Junran Wang, Xinjie Shen 沈鑫杰, Zehao Jin, Pan Li (2026). How Far Are VLMs from Privacy Awareness in the Physical World?. NeurIPS 2026.

PDF Code Project Page

Rongzhe Wei, Peizhi Niu, Xinjie Shen 沈鑫杰, Tong Tu, Yifan Li, Ruihan Wu, Eli Chien, Pin-Yu Chen, Olgica Milenkovic, Pan Li (2025). The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search. arXiv preprint.

PDF Project Page

Xinjie Shen 沈鑫杰 (2025). Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark. Preprint.

PDF Code Project Page

Xinjie Shen 沈鑫杰 (2025). Exploring ℓ0 Sparsification for Inference-free Sparse Retrievers. In SIGIR 2025.

Xinjie Shen 沈鑫杰 (2024). Cross-View Approximation on Grassmann Manifold for Multiview Clustering. In IEEE Transactions on Neural Networks and Learning Systems.

Xinjie Shen 沈鑫杰 (2024). FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model. In The Web Conference 2024.