39 citations · 41 across the 11 of their papers we have counts for
11 papers
When "Must" Becomes "Maybe": Erosion of Workflow Constraints in LLM Agent Handoffs
Yiheng Sun, Huifei Wang, Yancheng Zhu +3
Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downstream agent continue without revi…
MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs
Kevin Wang, Anna Thöni, Benjamin Kempinski +50
Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly underst…
Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues
Tao He, Lizi Liao, Yixin Cao +5
Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional t…
SPEED: Streaming Partition and Parallel Acceleration for Temporal Interaction Graph Embedding
Xi Chen, Yongxiang Liao, Yun Xiong +4
Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdepende…
RDGSL: Dynamic Graph Representation Learning with Structure Learning
Siwei Zhang, Yun Xiong, Yao Zhang +4
Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain…
iLoRE: Dynamic Graph Representation with Instant Long-term Modeling and Re-occurrence Preservation
Siwei Zhang, Yun Xiong, Yao Zhang +3
Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph mode…
Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddings
Yuxi Mi, Hongquan Liu, Yewei Xia +3
The emergence of vertical federated learning (VFL) has stimulated concerns about the imperfection in privacy protection, as shared feature embeddings may reveal sensitive informati…
TIGER: Temporal Interaction Graph Embedding with Restarts
Yao Zhang, Yun Xiong, Yongxiang Liao +4
Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic…
CLARE: A Semi-supervised Community Detection Algorithm
Xixi Wu, Yun Xiong, Yao Zhang +5
Community detection refers to the task of discovering closely related subgraphs to understand the networks. However, traditional community detection algorithms fail to pinpoint a p…
RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation
Yao Zhang, Yun Xiong, Yiheng Sun +4
Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with…
TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion
Yiheng Sun, Tian Lu, Cong Wang +4
The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to advocating financia…