5 papers
Activation Quantization of Vision Encoders Needs Prefixing Registers
Seunghyeon Kim, Taesun Yeom, Jinho Kim +3
Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications…
Decoupled Generative Modeling for Human-Object Interaction Synthesis
Hwanhee Jung, Seunggwan Lee, Jeongyoon Yoon +4
Synthesizing realistic human-object interaction (HOI) is essential for 3D computer vision and robotics, underpinning animation and embodied control. Existing approaches often requi…
Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective
Seunghyeon Kim, Kyeongryeol Go
Fisheye cameras introduce significant distortion and pose unique challenges to object detection models trained on conventional datasets. In this work, we propose a data-centric pip…
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal +76
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present th…
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Xuanchi Ren, Yifan Lu, Tianshi Cao +13
Collecting and annotating real-world data for safety-critical physical AI systems, such as Autonomous Vehicle (AV), is time-consuming and costly. It is especially challenging to ca…