AI.info

Xianglong Liu

Explore Xianglong Liu on AI.info.

• KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
• Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
• AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
• Uncovering Strategic Egoism Behaviors in Large Language Models
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning