AI.info
Jie Zhang
Explore Jie Zhang on AI.info.
- Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Prediction
- Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
- Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
- Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
- Towards Transferable Defense Against Malicious Image Edits
- TeachMaster: Generative Teaching via Code
- V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
- TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
- When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?
- SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition
- LLMscape