Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published 24 days ago • 36
view article Article Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers 22 days ago • 69
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16, 2025 • 124
Perception Encoder Collection OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated Sep 19, 2025 • 7
view article Article nanoVLM: The simplest repository to train your VLM in pure PyTorch +5 May 21, 2025 • 257
PaLI-3 Vision Language Models: Smaller, Faster, Stronger Paper • 2310.09199 • Published Oct 13, 2023 • 28