Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Paper • 2508.09192 • Published • 30
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding