Da Chen

This paper presents an open-source 5G testbed for simulating emergency alert spoofing attacks and proposes a cross-cell verification mechanism to detect single-source, potentially fake, warnings.

The paper proposes a unified geodesic framework that combines tangent-constrained priors with curvature regularization to improve the robustness of image segmentation, especially for complex shapes.

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at visual grounding, they struggle with fine-grained semantic following.

The paper introduces Knowledge-Intensive Video Generation (KIVI) as a challenging benchmark for evaluating video models on factuality and practical usefulness, showing that current state-of-the-art systems still struggle to match human performance.