Xinjie Shen
Tags
- Activation Steering 1
- Agent Evaluation 1
- Agent Safety 1
- Agentic AI 1
- Agentic RL 3
- AI Safety 2
- AI Security 2
- Application 1
- Awarded 1
- CKA-Agent 1
- Contextual Safety 2
- Diffusion 1
- E-Commerce 1
- EEG 1
- Embodied Agents 1
- Embodied AI 1
- Evaluation Benchmark 1
- Figure Design 1
- GAN 1
- Generative Model 1
- GNN 1
- Graph Neural Network 1
- Inference-Time Intervention 1
- Interesting 3
- Jailbreak 1
- Knowledge 1
- Large Language Models 1
- LLM 2
- LLM Safety 3
- Long-Horizon Agents 1
- Multi-Turn Dialogue 2
- Physical Environments 1
- Post-Training 1
- Privacy 2
- Publication 1
- Research Communication 1
- Runtime Defense 2
- Source Themes 3
- To-Read 1
- Tool-Using Agents 1
- TurnGate 1
- VAE 1
- Verifiable Environments 1
- VHD-Play 1
- Vision-Language Models 1