AI.info

Qing Wang

Explore Qing Wang on AI.info.

• All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
• Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
• Adversarial Attack on Black-Box Multi-Agent by Adaptive Perturbation
• Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval
• SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
• Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering