Search papers, labs, and topics across Lattice.
2
0
4
0
LLMs can now predict where drivers look with uncanny human-like accuracy, thanks to a new dataset and architecture that grounds attention in objects, not just scenes.
A single EEG decoding architecture, DSAINet, achieves state-of-the-art generalizability across diverse tasks and datasets without task-specific tuning, despite having only 77K parameters.
