Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
University of California
2
0
3
A quadtree visual tokenizer slashes token count for autoregressive image generation by adaptively focusing representational power on intricate image regions.
Cycle-consistent learning unlocks self-improvement in vision-language models, enabling them to reason about their own generations and boosting performance across understanding and generation tasks.