MeshioMeshio

multimodal-ai

2 articles tagged “multimodal-ai”, most recent first.

3
Sep 2, 20261 min read

Puffin-World brings physics and geometry into a unified 3D world model

Hugging Face’s Puffin-World combines gravity, depth, camera motion, and appearance to generate more consistent 3D scenes.

SenseTime previews NEO-unify, an encoder-free multimodal model
Aug 28, 20261 min read

SenseTime previews NEO-unify, an encoder-free multimodal model

NEO-unify combines native text and pixel processing in one end-to-end architecture, promising more efficient multimodal training.