Search papers, labs, and topics across Lattice.
3
0
6
6
QCPruner fuses two cross-modal cues into utility and applies it to both visual targets and candidate representatives within visual-affinity-based coverage, which achieves the highest average relative performance among evaluated complete-system pruning methods at every reported token budget.
Vision-language models struggle to uncover bugs in web applications, revealing a stark gap in their testing capabilities.
Coding agents can now be evaluated on their ability to navigate fuzzy requirements and interactive workflows, reflecting real-world software development challenges.
