Biao Yi
Scholar

Biao Yi

Google Scholar ID: qU8fx8IAAAAJ
Nankai University
LLM SecurityTrustworthy LLMSteganography
Google Scholar↗
Citations & Impact
All-time
Citations
199
 
H-index
8
 
i10-index
8
 
Publications
18
 
Co-authors
0
 
Contact
No contact links provided.
Publications
14 items
What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
2026
Cited
0
Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
2025
Cited
0
Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
2025
Cited
0
Gradient Surgery for Safe LLM Fine-Tuning
2025
Cited
0
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
2025
Cited
0
BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit
2025
Cited
0
Transform Before You Query: A Privacy-Preserving Approach for Vector Retrieval with Embedding Space Alignment
2025
Cited
0
Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
International Conference on Learning Representations · 2025
Cited
9
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)