Is Language Visual? An Experiment with Chinese Characters

Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning

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.

On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation

arXiv:2608. 11002v1 Announce Type: cross Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years.

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Langage Model

Visual Document Retrieval Goes Multilingual

How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment

arXiv:2608. 11816v1 Announce Type: cross Abstract: State-aligned distortion has been documented in China-origin text-based large language models (LLMs), but whether, and in what form, it arises in multimodal systems has not been systematically examined.

Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation

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...

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

Full Glyph Images Beat Token Embeddings: A Controlled Study for Transformers

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.

Seeing Red, Thinking Bad: Color Bias in Vision Language Models

arXiv:2608. 14286v1 Announce Type: cross Abstract: Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation.

Vision-Language Models are Fragile Multilingual Associators

arXiv:2608. 12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes.

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition

Ancient-Bench is a new benchmark for recognizing text on ancient Chinese artifacts, comprising 2,700 images that span 3,000 years of character evolution, nine artifact categories, and seven historical script forms. It introduces three annotation standards—symbol, character, and parsing standardization—to accommodate medium‑specific characteristics and enable consistent evaluation. Experiments show that current Vision‑Language Models and OCR specialists still struggle with variant characters, specialized symbols, and hallucination, indicating the task remains largely unsolved.