Search papers, labs, and topics across Lattice.
Huawei Noah鈥檚 Ark Lab 2 Harbin Institute of Technology 3 Nankai University
2
0
6
3
Forget expensive human feedback loops: a VLM-powered reward function can efficiently align image editing diffusion models with human preferences.
Spatial reasoning gets a major boost: OpenSpatial-3M, a new dataset, enables models to leapfrog existing benchmarks by 19%.