Search papers, labs, and topics across Lattice.
Shanghai Innovation Institute, Zhejiang University
4
0
6
Forget patch-based image tokenization: channel-wise quantization unlocks better codebook utilization and text-to-image generation by representing images as discrete levels of visual detail.
Freezing your vision foundation model doesn't have to mean sacrificing fine-grained detail: DecQ unlocks improved reconstruction and faster generative convergence with just 8 extra queries and minimal overhead.
Forget static coordination – robots that chat and dynamically re-plan can achieve a whopping 69% improvement in collaborative navigation success.
A 5B model just crushed the image generation and editing performance of models 5-16x larger, thanks to smarter feature fusion and a novel RL training strategy.
