Search papers, labs, and topics across Lattice.
Westlake University
3
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.
MLLMs that ace simple traffic rules still struggle when multiple rules interact, especially when they conflict, revealing a critical gap in their ability to handle real-world driving complexity.
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.
