104 citations · 149 across the 16 of their papers we have counts for
17 papers
Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Derui Wang, Zewei Shi, Rayne Holland +4
Debate distillation adapts weaker verifiers using multi-agent debate transcripts to improve their judgement in subsequent debates, but gains on monitored tasks do not establish rel…
Runtime Action Interference for AI Control of AlphaStar in StarCraft II
Jaymari Chua, Chen Wang, Liming Zhu +1
A trained reinforcement learning policy does not determine the complete behavior that users encounter: deployment code still schedules, admits, suppresses, or replaces its proposed…
Three-Body Alignment: Aligning Chess Agent with Human Reasoning through Reranked Rationale
Jaymari Chua, Chen Wang, Liming Zhu +1
As reasoning agents become increasingly complex, aligning their underlying reasoning and decision-making processes with human conceptual models is a challenge for AI security and s…
Retrieval-Augmented Review Generation for Poisoning Recommender Systems
Shiyi Yang, Xinshu Li, Guanglin Zhou +4
Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks, where malicious actors inject fake user profiles, including a group of wel…
DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
Shiyi Yang, Zhibo Hu, Xinshu Li +5
Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal r…
Learning Interpretable Scheduling Algorithms for Data Processing Clusters
Zhibo Hu, Chen Wang, Helen +3
Workloads in data processing clusters are often represented in the form of DAG (Directed Acyclic Graph) jobs. Scheduling DAG jobs is challenging. Simple heuristic scheduling algori…
Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning
Guanglin Zhou, Zhongyi Han, Shiming Chen +5
Recent studies indicate that large multimodal models (LMMs) potentially act as general-purpose assistants and are highly robust against different distributions. Despite this, domai…
Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
Shiyi Yang, Lina Yao, Chen Wang +2
Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks. Understanding attack tactics helps improve the robustness of RSs. We inten…
Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models
Zhibo Hu, Chen Wang, Yanfeng Shu +3
The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is conside…
HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization
Guanglin Zhou, Zhongyi Han, Shiming Chen +5
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features. In DG, the prevalent practice of constraining…
Emerging Synergies in Causality and Deep Generative Models: A Survey
Guanglin Zhou, Shaoan Xie, Guang-Yuan Hao +7
In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance. Deep generative models (DGMs) have prov…
Learning to Infer Counterfactuals: Meta-Learning for Estimating Multiple Imbalanced Treatment Effects
Guanglin Zhou, Lina Yao, Xiwei Xu +2
We regularly consider answering counterfactual questions in practice, such as "Would people with diabetes take a turn for the better had they choose another medication?". Observati…
Contrastive Counterfactual Learning for Causality-aware Interpretable Recommender Systems
Guanglin Zhou, Chengkai Huang, Xiaocong Chen +4
The field of generating recommendations within the framework of causal inference has seen a recent surge, with recommendations being likened to treatments. This approach enhances i…
Attn-HybridNet: Improving Discriminability of Hybrid Features with Attention Fusion
Sunny Verma, Chen Wang, Liming Zhu +1
The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers. Albeit powerful…
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
Huijun Wu, Chen Wang, Yuriy Tyshetskiy +3
Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep lea…
Interpreting Shared Deep Learning Models via Explicable Boundary Trees
Huijun Wu, Chen Wang, Jie Yin +2
Despite outperforming the human in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness r…
HPDedup: A Hybrid Prioritized Data Deduplication Mechanism for Primary Storage in the Cloud
Huijun Wu, Chen Wang, Yinjin Fu +3
Eliminating duplicate data in primary storage of clouds increases the cost-efficiency of cloud service providers as well as reduces the cost of users for using cloud services. Exis…