Search papers, labs, and topics across Lattice.
4
0
6
10
Self-Gating Attention achieves linear complexity in time series forecasting while maintaining competitive accuracy, revolutionizing the efficiency of attention mechanisms in this domain.
SAC$^2$-Net reveals that aligning motion-magnified and optical-flow representations through semantic anchors can significantly enhance micro-expression recognition performance.
LLM-derived user profiles can be powerfully leveraged for recommendation via a surprisingly simple distribution shaping approach, outperforming more complex fusion methods.
LLMs can guide the discovery of crucial structural features for routing in Mixture-of-Experts models, significantly boosting zero-shot graph anomaly detection.
