#vision-language-models

#…

2 posts

LiquidAI Ships LFM2.5-VL-3B: Edge-First Vision Beats the 4B Class

Liquid's new 3B vision-language model beats larger 4B competitors on grounding and screens, decodes 228 tok/s on an M5 Max, and ships with llama.cpp support day one. This is what edge-first design looks like.

#vision-language-models #edge-ai #multimodal #deployment #agents

NVIDIA's Nemotron OCR v2: How Synthetic Data Built a Multilingual Vision Powerhouse

NVIDIA just open-sourced a state-of-the-art OCR model trained almost entirely on synthetic data. Here's why that matters for the future of vision-language models.

#synthetic-data #ocr #vision-language-models #multilingual #open-source

Loading…