Failed to load scholar profile
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Paper '“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents' accepted to EMNLP 2025 main conference (oral)
- Paper 'An Engorgio Prompt Makes Large Language Model Babble on' accepted to ICLR 2025
- Paper 'One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training' accepted to ICCV 2024
- Preprint 'SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents' (arXiv:2509.23694)
- Preprint 'Towards Understanding the Cognitive Habits of Large Reasoning Models' (arXiv:2506.21571)
- Preprint 'Can Large Language Models Automate the Refinement of Cellular Network Specifications?' (arXiv:2507.04214)
- Reviewer for ICLR'26; Top Reviewer for NeurIPS'25; Notable Reviewer for ICLR'25
Co-authors: 0 (list not available)