Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
2
0
4
8
Forget retraining massive models: DPC-VQA shows you can adapt MLLMs to new video quality tasks with just a tiny calibration layer and a fraction of the data.
Forget small-scale image editing datasets – this work unleashes a million-scale human preference dataset that unlocks better reward models and boosts text-guided image editing performance.
