Daniel Dajun Zeng

As social media grows, harmful information spreads rapidly across platforms and evolves over time, showing cross-platform and cross-temporal variations. Existing methods rely on fixed model parameters during training, which fail to handle substantial semantic discrepancies, leading to Out-Of-Dist...

We observe that entropy in reinforcement learning functions analogously to the learning rate in LLMs. Maintaining stable entropy, as demonstrated in DAPO, helps stabilize RL training, while rapid entropy annealing (i.e., so-called entropy collapse) accelerates local performance improvement and en...

Deep hashing is widely used in large-scale image retrieval systems due to its efficient retrieval performance. However, its susceptibility to adversarial attacks limits its security in practical applications. Adversarial training is the most effective method for improving robustness, but it often...