Transition Models: Rethinking the Generative Learning Objective Paper • 2509.04394 • Published 5 days ago • 27
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing Paper • 2508.09192 • Published Aug 8 • 30
Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts Paper • 2508.07785 • Published 29 days ago • 25