3 papers
cs.AI2026
Belief Memory: Agent Memory Under Partial Observability
Junfeng Liao, Qizhou Wang, Jianing Zhu +3
LLM agents that operate over long context depend on external memory to accumulate knowledge over time. However, existing methods typically store each observation as a single determ…
cs.LG2026
Explainable LLM Unlearning Through Reasoning
Junfeng Liao, Qizhou Wang, Shanshan Ye +3
LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more e…
cs.CV2025
The Key of Parameter Skew in Federated Learning
Junfeng Liao, Sifan Wang, Ye Yuan +1
Federated Learning (FL) has emerged as an excellent solution for performing deep learning on different data owners without exchanging raw data. However, statistical heterogeneity i…