Search papers, labs, and topics across Lattice.
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China
2
0
2
Lowering energy barriers in neural training could revolutionize how we approach deep learning efficiency, achieving backpropagation-level performance with significantly reduced energy costs.
VecFormer slashes the computational cost of graph transformers while boosting out-of-distribution generalization by operating attention on quantized "graph tokens" instead of individual nodes.
