PLAY PODCASTS
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Daily Paper Cast · Jingwen Liang, Gengyu Wang

April 29, 202622m 29s

Audio is streamed directly from the publisher (media.transistor.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.