Tag: multimodal AI
Liquid AI branches six small models off one backbone
Mirendil says Fern 0.1 was trained for under $10M with agents writing more than 99 percent of the…
Google folds images and audio into one Gemma embedding space
EmbeddingGemma 2 puts text, code, pictures, video and sound on a single 768-dimension vector so retrieval systems stop…
Google Research hands video generation a bandit-driven director
Four agentic frameworks target the drift and cascading failures that break long AI video, and one of them…
Alibaba builds its first agent model to read video and audio
Qwen3.8-Omni-Flash handles audio and video together and calls tools on its own.
Tencent splits a voice agent into a brain and a cerebellum
Gander keeps a conversation alive in one model while a second model does the work.
Gemini Flash models now pick which video frames to watch
Google's agentic video processing cuts tokens by up to 88 percent on long recordings.
Meta’s Glimmer release puts desktop agents in reach
The Apache-licensed 30B model brings agentic AI to local machines.
Black Forest Labs debuts Flux 3 with video, audio, and robotic vision
The multimodal model generates images, 20-second video clips with sound, and even predicts physical actions from a single…