SearcharxivSearch

arXiv subjects

Zhanwei Wu

Publications and source records attributed to Zhanwei Wu.

2 recordsLinked to original sources

AIPC: Agent-Based Automation for AI Model Deployment with Qualcomm AI Runtime

Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, runtime integration, and accuracy validation. In practice, this workflow is long, failure-prone, and heavily dependent on deployment expertise, particularly when targeting hardware-specific inference runtimes. This technical report presents AIPC (AI Porting Conversion), an AI agent-driven approach for constrained automation of AI model deployment. AIPC decomposes deployment into standardized, verifiable stages and injects deployment-domain knowledge into agent execution through Agent Skills, helper scripts, and a stage-wise validation loop. This design reduces both the expertise barrier and the engineering time required for hardware deployment. Using Qualcomm AI Runtime (QAIRT) as the primary scenario, this report examines automated deployment across representative vision, multimodal, and speech models. In the cases covered here, AIPC can complete deployment from PyTorch to runnable QNN/SNPE inference within 7-20 minutes for structurally regular vision models, with indicative API costs roughly in the range of USD 0.7-10. For more complex models involving less-supported operators, dynamic shapes, or autoregressive decoding structures, fully automated deployment may still require further advances, but AIPC already provides practical support for execution, failure localization, and bounded repair.

cs.SE

BioMetaphor: AI-Generated Biodata Representations for Virtual Co-Present Events

In virtual or hybrid co-present events, biodata is emerging as a new paradigm of social cues. While it is able to reveal individuals' inner states, the technology-mediated representation of biodata in social contexts remains underexplored. This study aims to uncover human cognitive preferences and patterns for biodata expression and leverage this knowledge to guide generative AI (GenAI) in creating biodata representations for co-present experiences, aligning with the broader concept of Human-in-the-loop. We conducted a user elicitation workshop with 30 HCI experts and investigated the results using qualitative analysis. Based on our findings, we further propose a GenAI-driven framework: BioMetaphor. Our framework demonstration shows that current GenAI can learn and express visual biodata cues in an event-adpated, human-like manner. This human-centered approach engages users in research, revealing the underlying cognition constructions for biodata expression while demonstrating how such knowledge can inform the design and development of future empathic technologies.

cs.HC