Geonmin Kim

AI Research Engineer

Insight

A banner stating a 7x speedup, with inference latency cut from 1.6 seconds to 230ms. The figure comes from running GR00T N1.7 3B on a Qualcomm IQ-9075.

September 18, 2026

min read

Running VLA Without a GPU: 1.6s to 230ms on a Qualcomm NPU

min read

Deploying an Efficient Vision-Language Model on Mobile Devices

February 10, 2025

min read

Where do LLMs Encode the Knowledge to Assess the Ambiguity?

February 25, 2025

min read

A Study on Detecting LLM-Generated Multilingual Content

Culture

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.