4 papers
M100: An Orchestrated Dataflow Architecture Powering General AI Computing
Yan Xie, Changkui Mao, Changsong Wu +34
As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility…
Robotic Manipulation is Vision-to-Geometry Mapping: Vision-Geometry Backbones over Language and Video Models
Zijian Song, Qichang Li, Jiawei Zhou +4
At its core, robotic manipulation is a problem of vision-to-geometry mapping (). Physical actions are fundamentally defined by geometric properties like 3D posi…
MODIX: A Training-Free Multimodal Information-Driven Positional Index Scaling for Vision-Language Models
Ruoxiang Huang, Zhen Yuan
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniform…
OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language Models
Ruoxiang Huang, Xindian Ma, Rundong Kong +2
Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential struc…