Search papers, labs, and topics across Lattice.
Southeast University
3
0
7
Achieving 134 FPS with under 50 ms latency, ViCoStream redefines the capabilities of VideoLLMs for real-time streaming applications.
AdaSR achieves superior reasoning performance in dynamic environments by enabling models to adaptively allocate computation during streaming input.
Forget retraining: SHARPEN surgically repairs defects in neural networks by pinpointing faulty neurons with explainable AI and then fixing them with gradient-free optimization.
