Immersive network infrastructure is an integrated system of content representation, data transmission, and system resilience techniques designed to deliver digital experiences globally in a photorealistic, efficient, and reliable manner. However, traditional designs such as discrete content representation, handcrafted compression, and content-agnostic fault tolerance often fall short of these objectives. Although Artificial Intelligence (AI) offers promising solutions, AI systems often struggle to meet practical requirements when optimized solely from either the system or the AI perspective.

In this talk, I will showcase how to tackle this challenge with a co-design of AI and systems: (1) Measurements-driven System Design: Motivating system designs with AI model’s in-depth measurements and (2) Context-driven AI Design: Inspiring AI designs with the system’s context analysis. I will first present NeRFHub, a framework designed to serve emerging AI-driven representations (i.e., Neural Radiance Fields) to mobile devices for photo-realism. The key challenge is the prohibitive demand for computation and bandwidth resources of AI-driven representations. This research introduces a novel way for adapting AI-driven representations by formulating a multi objective optimization (MOO) problem, which is jointly solved with classic design space exploration techniques and fine-tuning of AI models. Furthermore, I will introduce LiFteR, a video streaming system powered by an AI-based video compression for bandwidth efficiency. The key limitation of existing AI-based video compression is its slow decoding speed, leading to issues such as rebuffering. LiFteR accelerates AI-based compression with a binary-tree-based workflow and a compatible codec design, enabling parallel processing of frames at the same tree level without compromising bandwidth efficiency.

Bo Chen is a postdoctoral researcher at University of Illinois at Urbana-Champaign (UIUC). He obtained his Ph.D. from UIUC advised by Prof. Klara Nahrstedt in 2022. Previously, he received his BS degree from Shanghai Jiao Tong University in 2016. His research interests include networking, machine learning systems, virtual reality, and mobile computing. His research has resulted in more than 20 publications and has been recognized by top conferences such as USENIX NSDI, ACM MobiCom, ACM MobiSys, and ACM SenSys. He received the best student paper award in ACM MMSys and the best paper award in IEEE ISM. He worked as the publication chair for IEEE SECON 2023 and NSF Workshop on Sustainable Computing for Sustainability 2024.