Search papers, labs, and topics across Lattice.
4
0
7
Tail latency in LLM serving can be cut by up to 50% without relying on length predictions, reshaping how we optimize inference performance.
Achieve faster and more accurate remote sensing interpretation by intelligently pruning visual tokens based on task-specific semantic and geometric importance, without any training.
Brain network analysis gets a dynamic upgrade: M3D-BFS adaptively fuses multi-modal data based on individual samples, boosting performance beyond static methods.
MLLMs struggle to effectively zoom into relevant details in ultra-high-resolution remote sensing imagery, but a new staged training framework can teach them when and where to focus for substantial accuracy gains.
