VLM Research · Field Notes

Hey, I'm Ru00y.

I work on vision-language models — building systems that see and read. This is my lab notebook: papers, projects, and late-night thoughts.

Read the blog About me

Recent writing

Research

All publications

under revision for TIP

DegEval: Benchmarking and Understanding Visual Degradation in Vision-Language Models

Jintao Gu, Guoshun Nan, Kaixiang Pan, Hanying Fu, et al.

Projects

Disaster Detection YOLO-based slope disaster detector Smart Security Alarm STM32 multi-sensor alarm system Structured Noun Caption Noun-guided image captioning Michigan DL for CV EECS 498-007 full coursework

Guestbook

Leave a message — comments are powered by GitHub Discussions.

Loading comments...