21 citations · 21 across the 3 of their papers we have counts for
7 papers
Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents
Yiming Xu, Qian Yang, Zihan Chen +4
Large language model (LLM) agents increasingly rely on external memory to accumulate past experiences for continual adaptation. However, effectively reusing memory requires accurat…
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Yiming Xu, Hongyue Yu, Beihua Yang +8
As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their reliable deployment. Existing…
TED: Related Party Transaction guided Tax Evasion Detection on Heterogeneous Graph
Yiming Xu, Bin Shi, Bo Dong +3
Tax evasion causes severe losses of government revenues and disturbs the economic order of fair competition. To help alleviate this problem, the latest tax evasion detection soluti…
Feature Bank Enhancement for Distance-based Out-of-Distribution Detection
Yuhang Liu, Yuefei Wu, Bin Shi +1
Out-of-distribution (OOD) detection is critical to ensuring the reliability of deep learning applications and has attracted significant attention in recent years. A rich body of li…
CLDG: Contrastive Learning on Dynamic Graphs
Yiming Xu, Bin Shi, Teng Ma +3
The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of th…
Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
Rui Zhao, Bin Shi, Jianfei Ruan +2
In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posterio…
GraphPub: Generation of Differential Privacy Graph with High Availability
Wanghan Xu, Bin Shi, Ao Liu +2
In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks. However, when an upstream data owner pub…