Zikai Song

VAKE reveals that over 80% of the knowledge activated through explicit priming is crucial for answering questions, showcasing a new pathway to enhance LLM factual accuracy.

Affective Stance integration boosts emotion recognition accuracy by 3.5% and pragmatic intent detection by 7.8%, revealing hidden layers of emotional communication in discourse.

SubdivAR achieves unprecedented accuracy in mesh subdivision, outperforming traditional methods by significantly enhancing detail retention and topology preservation.

Predicting comment popularity is more than just content quality – stylistic resonance with the platform's user base is a key ingredient, and this benchmark helps you measure it.

Achieve unbounded historical video association for popularity prediction without unbounded storage growth by clustering videos in a topology-aware memory bank and updating cluster features instead of storing individual videos.

Multi-object tracking gets a boost: HyperSSM leverages collaborative reasoning to maintain robust object trajectories, even when visual cues disappear.