LensVLM is an inference framework and post‑training recipe that lets Vision‑Language Models (VLMs) process compressed images of text by selectively expanding only the relevant parts back to full resolution. Using Qwen3.5‑9B‑Base, LensVLM achieves accuracy comparable to full‑text models at 4.3× compression and outperforms other compression baselines up to 10.1× across seven text QA benchmarks, while also improving performance on multimodal document and code tasks as compression increases.
By Roy Xie, Dan Friedman, Donghan Yu, Bowen Pan, Christopher Fifty, Jang-Hyun Kim, Xianzhi Du, Zhe Gan, Vivek Rathod, Bhuwan Dhingra
arXiv:2610.19443v1 Announce Type: new
Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual input...
By Haoyuan Wu, Aoqi Wu, Jiani Hu, Bei Yu
arXiv:2605.00809v3 Announce Type: replace
Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining...
By Yan Fang, Mengcheng Lan, Zilong Huang, Weixian Lei, Yunqing Zhao, Yujie Zhong, Yingchen Yu, Qi She, Yao Zhao, Yunchao Wei
arXiv:2608.30541v1 Announce Type: new
Abstract: Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent...
By Ran Zhang, Miryam de Lhoneux, Wessel Poelman
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
By Sangin Lee, Yukyung Choi
arXiv:2605. 16409v3 Announce Type: replace-cross Abstract: Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images containing small or degraded text, cluttered layouts, occlusion, handwriting, and complex typography.
By Qinwu Xu, Yifan Jiang, Haoyu Ren
arXiv:2607. 03994v1 Announce Type: cross Abstract: Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned.
By Shuyang Xiang, Hao Guan
arXiv:2610.09823v1 Announce Type: new
Abstract: Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string re...
By Deyuan Liu, Yihao Hu, Jingxuan Zhang, Xingying Li, Jun Xie, Jiacheng Liu, Jungang Li, Yu Huang, Xuanyi Liu, Yue Ding, Zecheng Wang, Lei Zhao, Mingda Wang, Zhenglin Cheng, Peng Sun, Tao Lin
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
By Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
MIXAR is the first generative multilingual pixel‑based language model, pretrained on eight high‑resource languages across Latin and CJK scripts with up to 0.5 B parameters. It replaces unstable adversarial training with a GRPO‑based reinforcement‑learning stage, improving free‑generation accuracy by up to 2.3× on multilingual benchmarks. MIXAR generalizes better to unseen low‑resource languages than a tokenizer‑based model trained on the same corpus, matches tokenizer models on discriminative tasks, and resists orthographic attacks more gracefully.
By Chen Hu, Yintao Tai, Antonio Vergari, Frank Keller, Alessandro Suglia
arXiv:2601. 09566v4 Announce Type: replace-cross Abstract: In this work, we study whether rendering Chinese characters as visual glyph images, rather than discrete token IDs as mainstream LLMs do, providing an inductive bias for character-level language modeling.
By Shuyang Xiang, Hao Guan
arXiv:2606. 14750v1 Announce Type: cross Abstract: Recent advances in pixel-based text modeling show that representing text as images enables models to exploit visual cues for language understanding.
By Adarsh Arigala, Arjun Gangwar, S Umesh, Yova Kementchedjhieva