Chunyu Wang

Ditch the pixel-perfect edits: letting multimodal models fully *reimagine* images based on semantic understanding yields massive quality gains in refinement tasks.

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.