From the 1 of 7 linked papers with an AI index.
7 papers
Let RGB Be the Language of Vision
Timing Yang, Jinrui Yang, Xinlong Li +11
The paper proposes a unified vision framework that encodes all visual signals—including images, masks, and depth maps—as RGB images, turning diverse tasks into a common RGB-to-RGB…
Captain Safari: A World Engine with Pose-Aligned 3D Memory
Yu-Cheng Chou, Xingrui Wang, Yitong Li +5
World engines aim to synthesize long, 3D-consistent videos that support interactive exploration of a scene under user-controlled camera motion. However, existing systems struggle u…
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
Feng Wang, Yaodong Yu, Guoyizhe Wei +4
Since the introduction of Vision Transformer (ViT), patchification has long been regarded as a de facto image tokenization approach for plain visual architectures. By compressing t…
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
Yunfei Xie, Ce Zhou, Lang Gao +8
This paper introduces MedTrinity-25M, a comprehensive, large-scale multimodal dataset for medicine, covering over 25 million images across 10 modalities with multigranular annotati…
ARFlow: Autoregressive Flow with Hybrid Linear Attention
Mude Hui, Rui-Jie Zhu, Songlin Yang +5
Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compres…
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
Feng Wang, Timing Yang, Yaodong Yu +7
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representation…