FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Paper
•
2601.23182
•
Published
•
20
Ying Zhu
Auraithm
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
9 days ago
MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models
upvoted
a
paper
12 days ago
MOVA: Towards Scalable and Synchronized Video-Audio Generation
authored
a paper
12 days ago
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Organizations
authored
2
papers
12 days ago
authored
a
paper
about 2 months ago