AOS: Agent Operating System
A research prototype for agent collaboration through runtime primitives: artifacts, messaging, capabilities, and scheduling.
Research, images, and thoughtful experiments.
Peihong Guo is a research engineer working across graphics, AI, and visual computing. This site gathers selected projects, blog posts, and photographic studies in a stripped-back editorial frame.
Current focus
Building computer vision and graphics systems, then documenting the interesting pieces with clarity.
Selected work
Featured projects
Jarvis Voice Assistant
An Android voice assistant with local Qwen inference, speech models, home-control tools, and a background update pipeline.
Generative Facial Keypoints
Exploring image-conditioned diffusion and flow matching for facial landmarks with frozen DINO features and transformer coordinate models.
Personal Projects
Some personal projects for fun over the years.
Recent writing
Blog highlights
Deploying Qwen on Intel Arc with vLLM and DFlash2
Serving a quantized Qwen model on a single 32 GB Intel GPU: cache budgets, speculative decoding, long-context performance, and deployment lessons.
Building Jarvis: A Local Voice Assistant with Android and Hermes
A turn-based voice assistant combining Android wake detection, local speech models, Qwen inference, verified home-control tools, and a background update pipeline.
Adding Meshes, BVHs, and Photon Mapping to My Browser Ray Tracer
The follow-up to the ray tracer refactor: Stanford bunnies, CPU photon mapping, world-space caustics, and a lot of renderer debugging.