Jiawen Shi
4 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
large language model
(3)
backdoor attack
(2)
decision making
(1)
autonomous driving
(1)
model merging
(1)
synthetic data generation
(1)
adversarial attack
(1)
multimodal large language model
(1)
tool selection
(1)
utility preservation
(1)
agent safety
(1)
threat model
(1)
multi-agent system
(1)
parameter fusion
(1)
adversarial learning
(1)
token-level attack
(1)
model security
(1)
Papers
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
ACL 2026
BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
CVPR 2025
Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
ACL 2025
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
ICLR 2024