Search papers, labs, and topics across Lattice.
School of Cyber Science and Technology, Shandong University,
5
0
6
0
Image-level deepfake detectors can outperform traditional video-level detectors, with one achieving a remarkable 93.80% AUC when adapted for video analysis.
HERALD shifts traffic safety from reactive mapping of past crashes to proactive forecasting of emerging hotspots, enabling timely interventions.
YouZhi-LLM achieves unprecedented concurrency and accuracy in financial LLMs by dramatically reducing KV-cache overhead, setting a new standard for deployment efficiency.
Despite advances in vision-language models, they still struggle to reason about the complex dynamics of traffic crashes, highlighting a critical gap in safety-critical applications.
Image generation models exhibit a surprising "Order-to-Space Bias," meaning the order you mention objects in a prompt can drastically alter their placement in the generated image, even overriding other visual cues.
