11 papers
Generative Optimization for Incentivized Advertising with Global Level Constraints
Gege Chen, Ning Luo, Hao Jiang +7
Incentivized advertising allocates monetary or virtual rewards to drive user engagement, where a key challenge is optimizing continuous incentive magnitudes under strict global con…
Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It
Wenxin Tai, Yaqian Liu, Ting Zhong +1
Recent work has observed that explanations produced by Self-Interpretable Graph Neural Networks (SI-GNNs) can be self-inconsistent: when the model is reapplied to its own explanato…
AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
Jian Lang, Rongpei Hong, Ting Zhong +1
Deploying multimodal systems in real-world environments often entails handling modality-missing scenarios, where one or more modalities are unavailable. While recent studies addres…
Guidance Is Not a Hyperparameter: Learning Dynamic Control in Diffusion Language Models
Fan Zhou, Tim Van de Cruys
Classifier-Free Guidance (CFG) is a widely used mechanism for controlling diffusion-based generative models, yet its guidance scale is typically treated as a fixed hyperparameter t…
Decompose to Understand, Fuse to Detect: Frequency-Decoupled Anomaly Detection for Encrypted Network Traffic
Xinglin Lian, Chengtai Cao, Ting Zhong +3
Network traffic anomaly detection represents a critical cybersecurity task, yet widespread encryption makes this task increasingly challenging. In response, image-based methods tha…
Shedding the Facades, Connecting the Domains: Detecting Shifting Multimodal Hate Video with Test-Time Adaptation
Jiao Li, Jian Lang, Xikai Tang +6
Hate Video Detection (HVD) is crucial for online ecosystems. Existing methods assume identical distributions between training (source) and inference (target) data. However, hateful…