From the 1 of 6 linked papers with an AI index.
6 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…
RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers
Timing Yang, Predrag Neskovic, Jansen Seheult +4
When humans see a bird, they recognize far more than just "bird" -- they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every…
Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
Timing Yang, Sicheng He, Hongyi Jing +4
SAM 3D Body (3DB) achieves state-of-the-art accuracy in monocular 3D human mesh recovery, yet its inference latency of several seconds per image precludes real-time application. We…
ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access
Timing Yang, Sucheng Ren, Alan Yuille +1
Text-to-video generation has surged in interest since Sora, yet open-source models still face a data bottleneck: there is no large, high-quality, easily obtainable video-text corpu…
RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models
Timing Yang, Guoyizhe Wei, Alan Yuille +1
Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we sys…
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…