Structure over Pixels: Learning Variable-Length Visual Programs 事件

Structure over Pixels: Learning Variable-Length Visual Programs arXiv:2605.27696v1 Announce Type: new Abstract: Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenizers either require post-hoc search or select among a discrete set of pre-trained rates, rather than learning a continuous per-image sequence length coupled to the model and scene, and they typically train aga