Huazheng Wang
huazhengwang
AI & ML interests
Reinforcement Learning, Information Retrieval, LLM Agent.
Recent Activity
authored
a paper
about 1 month ago
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
authored
a paper
about 1 month ago
A Common Pitfall of Margin-based Language Model Alignment: Gradient
Entanglement
authored
a paper
about 1 month ago
LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
Organizations
None yet