Search papers, labs, and topics across Lattice.
Fudan University
2
0
6
0
ReviewDSE achieves a 1.78% reduction in wirelength while exposing and repairing design flaws that traditional methods miss.
Masking just 5% of attention heads in vision-language models tanks performance on long-context tasks, revealing a surprisingly sparse and critical set of "multimodal retrieval heads" that attend to both text and images.
