Tagged: multimodal

15 articles

Latest

DeepSeek's Flash Vision Model Nearly Ties Opus 4.8 on Agent Benchmarks

ChatGPT gets eyes and ears, rolling out now to paid users

OpenAI launches GPT-4o, gives free ChatGPT users the good stuff

OpenAI's GPT-4o safety report: Persuasion gets a 'medium' risk rating

OpenAI drops free multimodal moderation model with 42% accuracy bump

OpenAI lets you fine-tune GPT-4o with images, and yes, it's a big deal

GPT-4o can now generate images — and it's a whole different beast

OpenAI bakes image gen into GPT-4o, and it can actually read

NVIDIA's new AI safety model can now enforce custom rules, not just a one-size-fits-all policy

Google's Gemma 4 packs GPT-rivaling power into a 4B-parameter model

Google's Gemma 3n Crams 5B-Parameter Brains Into Just 2GB of VRAM

Meta drops Llama Guard 4: a 12B safety model that runs on a single GPU

Hugging Face shrinks video AI to 256M params — and it actually works

The world’s smallest VLM is here at 256M parameters, beating 80B models from 17 months ago

Google drops PaliGemma 2 vision models up to 28B parameters with 896px resolution