Search papers, labs, and topics across Lattice.
Email:
4
0
4
The interaction between selection and aggregation in sparse attention networks can lead to super-resolution gains that are greater than the sum of their parts, challenging conventional wisdom in model design.
MambaPSA achieves a remarkable 17.6% boost in CPU inference speed while maintaining competitive accuracy in YOLO26, showcasing the potential of state space models in object detection.
YOLO-AMC achieves an unprecedented mAP of 0.9917 for crack detection, setting a new benchmark in the field.
Forget retraining LLMs from scratch for new architectures: PromptEmbedder lets you adapt to new backbones by only retraining a lightweight linear alignment matrix, slashing memory by 40% and speeding up training by 3.7x.
