Search papers, labs, and topics across Lattice.
Nanjing University
5
0
6
Automating data selection with DataMaster not only reduces manual effort but also enhances performance across diverse applications, challenging traditional heuristic methods.
GARI enables a flexible, learnable interface that maintains transformation consistency across diverse data types, challenging the rigidity of traditional equivariant architectures.
EDA not only corrects the current memory write but also actively removes outdated information, leading to superior performance in long-context scenarios.
YOLO can learn faster and better by strategically skipping redundant images during training, achieving a 1.43x speedup and improved accuracy with a new Anti-Forgetting Sampling Strategy.
Achieve SOTA multi-modal object tracking by adaptively fusing modalities with a Mixture of Experts and decoupling temporal propagation with separate State Space Models.
