Cite
Notes
Only stored in your browser.
Attribution
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
arXiv 2026
WavFlow: Audio Generation in Waveform Space
from 2 papers
Shoufa Chen
Yuren Cong
Zhiheng Liu
Fanny Yang
Feiyan Zhou
Jonas Schult
Luke Zettlemoyer
professor
Luyuan Wang
Mengzhao Chen
Ping Luo