Search papers, labs, and topics across Lattice.
3
0
5
Video-ToC drastically improves video understanding by forcing Video LLMs to focus on relevant visual cues, leading to state-of-the-art performance and reduced hallucinations.
Amodal SAM unlocks zero-shot amodal segmentation by adapting the Segment Anything Model (SAM) to infer complete object shapes, even in the presence of occlusions.
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.
