Search papers, labs, and topics across Lattice.
5
32
7
9
Decomposing image editing tasks into meta-tasks and aligning model reasoning with editing behavior unlocks surprising generalization to unseen editing operations.
Ditch the byte-level baggage: HiVG's hierarchical tokenization for SVGs slashes token redundancy and coordinate hallucinations, paving the way for more efficient and geometrically sound vector graphics generation.
Autoregressive video generation gets a 1.8x speed boost and avoids temporal drift by denoising all blocks hierarchically at the same noise level.
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.
