Lijun Li
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
arXiv 2026
Toward Efficient Agents: Memory, Tool learning, and Planning
arXiv 2026
DeepSight: An All-in-One LM Safety Toolkit
arXiv 2026
T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
CVPR 2025 1
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
arXiv 2025
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
arXiv 2025
ProGuard: Towards Proactive Multimodal Safeguard
arXiv 2025
EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
arXiv 2024
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
arXiv 2024
RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation
ICCV 2023 1
Affiliations
Frequent co-authors
10from 10 papers