4 papers
Scalable Context Orchestration for Serving LLMs Over Voice
Linyi Jiang, Silvery D. Fu, Yifei Zhu
Voice AI applications are gaining popularity as advances in large language models (LLMs) enable more natural and accessible spoken interactions. Serving these applications requires…
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Chenxi Li, Xianggan Liu, Dake Shen +9
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elici…
Hyperion: Low-Latency Ultra-HD Video Analytics via Collaborative Vision Transformer Inference
Linyi Jiang, Yifei Zhu, Hao Yin +1
Recent advancements in array-camera videography enable real-time capturing of ultra-high-definition (Ultra-HD) videos, providing rich visual information in a large field of view. H…
Janus: Collaborative Vision Transformer Under Dynamic Network Environment
Linyi Jiang, Silvery D. Fu, Yifei Zhu +1
Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Network architectures and achieved state-of-the-art results in various computer vision tasks. Since Vi…