AI.info

Ying Wen

Explore Ying Wen on AI.info.

• MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
• EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
• Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
• MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
• When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
• ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling