Search papers, labs, and topics across Lattice.
Harbin Institute of Technology
3
0
5
CouCE achieves state-of-the-art performance in debiased deep metric learning by simultaneously neutralizing both background and foreground confounders.
Steer LVLMs' attention with caption guidance and watch object hallucinations drop by 6%—no training required.
Reconstructing 3D scenes from images obscured by smoke and extreme darkness is now significantly more achievable, thanks to insights gleaned from the NTIRE 2026 challenge.
