Papers4

All Beginner Intermediate Advanced

All Sources arXiv

#document understanding

GutenOCR: A Grounded Vision-Language Front-End for Documents

Intermediate

Hunter Heidenreich, Ben Elliott et al.Jan 20arXiv

GutenOCR turns a general vision-language model into a single, smart OCR front-end that can read, find, and point to text on a page using simple prompts.

#grounded OCR#vision-language model#document understanding

STEP3-VL-10B Technical Report

Beginner

Ailin Huang, Chengyuan Yao et al.Jan 14arXiv

STEP3-VL-10B is a small (10 billion parameters) open multimodal model that sees images and reads text, yet scores like much larger models.

#multimodal foundation model#unified pre-training#perception encoder

InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search

Intermediate

Kaican Li, Lewei Yao et al.Dec 21arXiv

This paper builds a tough new test called O3-BENCH to check if AI can truly think with images, not just spot objects.

#multimodal reasoning#generalized visual search#reinforcement learning

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

Intermediate

Hongbo Zhao, Meng Wang et al.Dec 17arXiv

Long texts are expensive for AI to read because each extra token costs a lot of compute and memory.

#vision‑text compression#VTCBench#vision‑language models