Junru Ren 任俊儒

Junru Ren 任俊儒

MIT EECS M.S. and MBA Candidate, MIT LGO '26

Posts by Tags

class

Cheatsheet for Your MIT Sloan Classes

1 minute read

Published:

Hi there. If you wind up on this page, I assume you’re busy studying for your upcoming MBA Core exams at MIT Sloan.

6.8300 Final Project: Taming CLIP’s Captioning Bias: A COCO-Driven Analysis and Permutation Ensemble

20 minute read

Published:

Abstract: Vision-language models like CLIP struggle with multi-object scenes, often favoring prominent objects or those mentioned first in captions. Using real-world COCO images, we show that CLIP’s caption-matching accuracy drops from 91.23% to 87.45% when object order is reversed. To address this, we explore a post-hoc mitigation: a permutation ensemble that averages scores across all object orders, boosting robustness and recovering accuracy to 90.04%. Our findings reveal persistent order biases and offer a simple, effective strategy to improve CLIP’s reliability in complex scenes.

computer vision

6.8300 Final Project: Taming CLIP’s Captioning Bias: A COCO-Driven Analysis and Permutation Ensemble

20 minute read

Published:

Abstract: Vision-language models like CLIP struggle with multi-object scenes, often favoring prominent objects or those mentioned first in captions. Using real-world COCO images, we show that CLIP’s caption-matching accuracy drops from 91.23% to 87.45% when object order is reversed. To address this, we explore a post-hoc mitigation: a permutation ensemble that averages scores across all object orders, boosting robustness and recovering accuracy to 90.04%. Our findings reveal persistent order biases and offer a simple, effective strategy to improve CLIP’s reliability in complex scenes.

latex

Tutorial: Use LaTeX Locally with VS Code

6 minute read

Published:

This post is a quick guide to setting up LaTeX on your own computer, so you can write papers, resumes, or dazzling “class notes” using LaTeX locally—without relying on Internet connectivity. In other words, you won’t be tied to Overleaf: you can bring your laptop anywhere and keep working on your next big ideas.

mit

Cheatsheet for Your MIT Sloan Classes

1 minute read

Published:

Hi there. If you wind up on this page, I assume you’re busy studying for your upcoming MBA Core exams at MIT Sloan.

6.8300 Final Project: Taming CLIP’s Captioning Bias: A COCO-Driven Analysis and Permutation Ensemble

20 minute read

Published:

Abstract: Vision-language models like CLIP struggle with multi-object scenes, often favoring prominent objects or those mentioned first in captions. Using real-world COCO images, we show that CLIP’s caption-matching accuracy drops from 91.23% to 87.45% when object order is reversed. To address this, we explore a post-hoc mitigation: a permutation ensemble that averages scores across all object orders, boosting robustness and recovering accuracy to 90.04%. Our findings reveal persistent order biases and offer a simple, effective strategy to improve CLIP’s reliability in complex scenes.

mitsloan

Cheatsheet for Your MIT Sloan Classes

1 minute read

Published:

Hi there. If you wind up on this page, I assume you’re busy studying for your upcoming MBA Core exams at MIT Sloan.

projects

6.8300 Final Project: Taming CLIP’s Captioning Bias: A COCO-Driven Analysis and Permutation Ensemble

20 minute read

Published:

Abstract: Vision-language models like CLIP struggle with multi-object scenes, often favoring prominent objects or those mentioned first in captions. Using real-world COCO images, we show that CLIP’s caption-matching accuracy drops from 91.23% to 87.45% when object order is reversed. To address this, we explore a post-hoc mitigation: a permutation ensemble that averages scores across all object orders, boosting robustness and recovering accuracy to 90.04%. Our findings reveal persistent order biases and offer a simple, effective strategy to improve CLIP’s reliability in complex scenes.

tutorial

Tutorial: Use LaTeX Locally with VS Code

6 minute read

Published:

This post is a quick guide to setting up LaTeX on your own computer, so you can write papers, resumes, or dazzling “class notes” using LaTeX locally—without relying on Internet connectivity. In other words, you won’t be tied to Overleaf: you can bring your laptop anywhere and keep working on your next big ideas.

vscode

Tutorial: Use LaTeX Locally with VS Code

6 minute read

Published:

This post is a quick guide to setting up LaTeX on your own computer, so you can write papers, resumes, or dazzling “class notes” using LaTeX locally—without relying on Internet connectivity. In other words, you won’t be tied to Overleaf: you can bring your laptop anywhere and keep working on your next big ideas.