-
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 100 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 114 -
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Paper • 2512.23447 • Published • 93 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 64