Zhiqiang Wang

Tree search on on-policy trajectories dramatically boosts policy gradient learning by uncovering rare high-return paths, outperforming PPO on Atari and MuJoCo with minimal bias increase.

Activating 62% fewer experts without sacrificing significant accuracy could revolutionize the efficiency of Mixture-of-Experts models in real-world applications.

Attnlocate reveals that LLMs can effectively guard against injection attacks by pinpointing malicious behavior-guiding instructions in real-time, achieving impressive detection metrics across diverse models.

A novel filtering strategy can drastically enhance the stealth of network covert channels, making them far more resilient against detection.