Paper recorded by Signals 4 on 2026-10-27 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-27 on arXiv · recorded by Signals 4 on 2026-10-28
Category: cs.CV · 计算机视觉 · first seen 2026-10-28
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective. However, quantization error is widely assumed to cause unavoidable semantic loss, fundamentally limiting the semantic fidelity of discrete visual tokens and positioning continuous visual representations as an intrinsic