Get started
Author

Qianli Ma

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
2026 · Chua, Shei Pern, Wu, Hao, et al. · arXiv (Cornell University) · 3
PDF
Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds
2026 · Jiahao Chen, Rui Yin, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2
PDF
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
2026 · Association for Computational Linguistics 2026, Bai, Tong, et al. · Underline Science Inc.
Human-Agent Collaborative Paper-to-Page Crafting
2026 · Association for Computational Linguistics 2026, ., Siyuwang, et al. · Underline Science Inc.
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance
2026 · Association for Computational Linguistics 2026, ., Siyuwang, et al. · Underline Science Inc.
OmniScale: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
2026 · Association for Artificial Intelligence 2026, Bin Jia, Bin, et al. · Underline Science Inc.
Works count: 6
Citation count: 5
H-index: 2
I10-index:
Year
Topic
Type