Poster · Sydney
Diffusion-State Policy Optimization for Masked Diffusion Language Models
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Daisuke Oba, Hiroki Furuta, Naoaki Okazaki
- Organisations
- Institute of Science Tokyo, Google DeepMind
- QRS classification
- Reinforcement learning, Language models, Generative models