Jilong Liu

Identifiers

• name variant Jilong Liu 0.60 · backfill

Papers (4)

1. Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection cs.CV · 2026 · author #3
2. CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment cs.LG · 2026 · author #1
3. Controllable Value Alignment in Large Language Models through Neuron-Level Editing cs.LG · 2026 · author #4
4. Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control cs.LG · 2026 · author #3

Mentions

• 2606.01843 #3 · arxiv_oai · confidence 0.70 Jilong Liu
• 2602.07356 #4 · arxiv_oai · confidence 0.70 Jilong Liu
• 2603.07211 #1 · arxiv_oai · confidence 0.70 Jilong Liu
• 2602.07340 #3 · arxiv_oai · confidence 0.70 Jilong Liu

Frequent Coauthors

• Yonghui Yang 4 shared papers
• Le Wu 3 shared papers
• Richang Hong 3 shared papers
• Fengbin Zhu 2 shared papers
• Tat-Seng Chua 2 shared papers
• Weibiao Huang 2 shared papers
• Wenjian Tao 2 shared papers
• Yihui Wang 2 shared papers
• Haokai Ma 1 shared papers
• Hao Zhan 1 shared papers
• Junfeng Fang 1 shared papers
• Junwei Li 1 shared papers
• Pengyang Shao 1 shared papers
• Tat-Sent Chua 1 shared papers
• Wei Qin 1 shared papers
• Xingyu Zhu 1 shared papers