Xiaomi-Robotics-U0 Collection Unified embodied synthesis model that bridges foundation image generation and embodied world modeling • 2 items • Updated 10 days ago • 10
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget Paper • 2607.13125 • Published 5 days ago • 136
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 15 days ago • 64
KVAE 2.0 Collection KVAE 2.0 is a family of video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16 • 2 items • Updated Apr 16 • 5
KVAE-Audio Collection KVAE-Audio is a continuous full-band audio waveform autoencoder • 1 item • Updated 24 days ago • 7
LTX-2.3 Creative Lab Collection LoRAs and IC-LoRAs, trained on the LTX-2.3 model • 25 items • Updated 4 days ago • 78