Search papers, labs, and topics across Lattice.
2
0
6
3
Forget hand-annotated visual reasoning datasets: VG-CoT leverages a fully automated pipeline to generate grounded, step-by-step reasoning, enabling scalable and cost-efficient training of more trustworthy LVLMs.
Existing translation quality estimation models exhibit systematic gender bias, but FairQE shows you can fix this without hurting overall accuracy.
