view article Article LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR By lightonai and 2 others • 3 days ago • 45
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale Paper • 2510.14979 • Published 10 days ago • 64
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published 10 days ago • 67
ERNIE 4.5 Collection collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 26 items • Updated Sep 24 • 174
PaddleOCR-VL Collection Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model • 3 items • Updated 9 days ago • 16
Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps Paper • 2510.13430 • Published 11 days ago • 1
mixedbread-ai/mxbai-edge-colbert-v0-32m Sentence Similarity • 31.9M • Updated 9 days ago • 11.8k • • 20
mixedbread-ai/mxbai-edge-colbert-v0-17m Sentence Similarity • 16.8M • Updated 9 days ago • 45.3k • • 21
view article Article mem-agent: Equipping LLM Agents with Memory Using RL By driaforall and 1 other • 17 days ago • 30
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play Paper • 2509.25541 • Published 27 days ago • 136
BERT Hash Nano Models Collection Set of BERT models with a modified embeddings layer • 3 items • Updated 20 days ago • 8