This work introduces IDSpect, which deterministically decomposes the target text into IDS tokens and aligns crop-level visual IDS predictions with the target sequence, and achieves leading structural quality and semantic alignment on LongText and GenTextEval.
Ya-Zhen Xie, Xing-Song Ye, Zhi-Neng Chen· arXiv.org· 1 citation
Vision-Language-Action (VLA) models have shown strong capabilities in robotic manipulation, yet existing benchmarks typically assume that task-relevant information is explicitly specified in the instruction. In practice, however, humans frequently refer to objects, quantities, and relations implicitly, requiring robots...
Autoregressive models via next token prediction have emerged as a promising way towards unified models across multiple modalities for general artificial intelligence. Nevertheless, exploiting this idea to achieve single image to 3D generation remains a challenging problem. In this paper, we introduce a new Autoregressi...
Hai-Bo Yang, Yang Chen, Ying-Wei Pan et al.· IEEE Transactions on Pattern...· 0 citations
This work constructs TextMuSS-10M, a large-scale synthetic scene text dataset spanning 10 scripts and 229 languages and proposes ScriptMoE, a script-aware Mixture-of-Experts (MoE) architecture that achieves the highest accuracy and is simpler than per-language experts, lighter than VLMs, and more accurate than both.
Xing-Song Ye, Yong-Kun Du, Jia-Xin Zhang et al.· 1 citation
Perceptual Flow Matching supervises flow matching in a perceptual feature space using pretrained perceptual models, which substantially improves the few-step generation capability of flow-matching models, reducing the number of sampling steps from 35-50 to 4-8 while preserving generation quality.
Chuyang Zhao, Yifei Song, Hongfa Wang et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.