Tongtian Yue

GenCue: Generation-Oriented Video Captions for High-Fidelity Text-to-Video

Divid: Disentangled Spatial-Temporal Modeling within LLMs for Temporally Grounded Video Understanding

LaVi: Efficient Large Vision-Language Models via Internal Feature Modulation

Ada-K Routing: Boosting the Efficiency of MoE-based LLMs

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

EEGPT: Unleashing the Potential of EEG Generalist Foundation Model by Autoregressive Pre-training