Search papers, labs, and topics across Lattice.
3
32
5
4
Decomposing image editing tasks into meta-tasks and aligning model reasoning with editing behavior unlocks surprising generalization to unseen editing operations.
Forget brittle text-based reasoning: GVCoT unlocks more precise image editing by generating and optimizing visual reasoning cues directly within the image domain.
The largest open-source image generative model to date, HunyuanImage 3.0, achieves state-of-the-art performance using a Mixture-of-Experts architecture and native Chain-of-Thoughts schema.
