GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Paper • 2605.29398 • Published • 4
Aiden Williams
aiden-williams
AI & ML interests
Alignment-focused model research.
Recent Activity
upvoted a paper about 17 hours ago
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models liked a model about 21 hours ago
Snehanjan/llama-3.2-3b-spider-text-to-sql liked a dataset 3 days ago
fka/prompts.chatOrganizations
None yet
