Search papers, labs, and topics across Lattice.
5
0
7
Monolithic 3D scenes with hundreds of heavily occluded objects can be cleanly parsed into individual editable meshes without ever training on multi-object data.
On-demand safety interventions can significantly improve the performance of vision-language models without sacrificing their multimodal reasoning capabilities.
SafeCap boosts LVLM safety by up to 19 points through innovative caption-mediated reinforcement learning, outpacing traditional alignment methods.
Achieving high-quality low-light imaging without the need for clean RGB data could revolutionize how we approach image enhancement in challenging environments.
Surprise Forcing redefines resource allocation in video generation, leading to improved visual quality and consistency without sacrificing streaming speed.
