Search papers, labs, and topics across Lattice.
5
0
6
Explicitly learning spatial priorities boosts infrared target detection performance, achieving up to 89.00 F1 score with real-gaze supervision.
Achieving a 62.29% action match in offline VLN tasks, PGN redefines the benchmarks for multimodal navigation systems.
MR-GVNO achieves millisecond-level full-field inference for complex plate structures without the need for labeled data, revolutionizing rapid response predictions in engineering applications.
Physics-informed neural operators can now learn continually without forgetting, thanks to a simple replay strategy that preserves past knowledge while rapidly adapting to new out-of-distribution data.
By explicitly modeling motion with a retina-inspired mechanism, MI-DETR achieves a remarkable +26.35 mAP@50 improvement over the best multi-frame baseline for infrared small target detection.
