Search papers, labs, and topics across Lattice.
6
0
8
5
Strong 3D perception and competitive motion planning in autonomous driving are achieved without sacrificing general vision-language understanding.
SpatialCrafter achieves unprecedented 3D consistency in image-to-scene generation, effectively eliminating long-term drift and enhancing detail fidelity.
Achieving a 3.09 percentage-point accuracy gain while reducing model size by 80% demonstrates the power of cross-architecture knowledge distillation in precision agriculture.
Relative calibration can significantly enhance the evaluation of memory consistency in video world models, revealing that traditional metrics may overlook critical distinctions.
Unleashing LLMs to "paint" with code lets you directly manipulate image generation, moving beyond black-box prompt engineering.
One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.
