Get started
Author

Weixiang Zhao

Observed institution: Harbin Institute of Technology
OpenAlex ID: A5139836280
L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
2025 · Xiaohao Liu, Xiaobo Xia, et al. · neural information processing systems · 1
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
2026 · Jiahe Guo, Xiangran Guo, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
On Safety Risks in Experience-Driven Self-Evolving Agents
2026 · Weixiang Zhao, Yichen Zhang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
2026 · Xing Fu, Yulin Hu, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
2026 · Xingyu Sui, Yanyan Zhao, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
2025 · jingnan zheng, Xiangtian Ji, et al. · neural information processing systems
Works count: 6
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type