Search papers, labs, and topics across Lattice.
Xiamen University
3
0
2
QCA selects the most relevant frames from long videos, achieving superior performance with half the data of previous methods.
CausalMem achieves over 20x visual token compression while maintaining high accuracy in streaming video understanding, redefining memory efficiency in MLLMs.
AdaQ enables MLLMs to achieve superior long video understanding with just 64 frames, outperforming state-of-the-art methods by a striking margin.
