Yash Raj Suman - Labellerr

Yash Raj Suman

How Autonomous Vehicles Perceive the World?

computer vision

How Computer Vision Powers Autonomous Vehicles

Computer vision helps self-driving cars “see” and understand their surroundings using AI, cameras, LiDAR, and radar. It powers object detection, lane tracking, and decision-making in real time, making autonomous vehicles smarter, safer, and ready for complex road conditions.

Evaluating LLMs

Opik Is Changing How You Evaluate LLMs — Find Out How

Opik by Comet automates LLM evaluation, detects errors and hallucination. It tracks decisions, flags mistakes, and removes manual testing.

Fine-tune Yolo for pose estimation

computer vision

How To Fine-Tune YOLO For Pose Estimation On Custom Dataset

Fine-tuning YOLO for pose estimation on a custom dataset allows for precise keypoint detection tailored to specific applications like sports analytics, healthcare, and robotics. In this guide, we cover everything from dataset annotation and keypoint formatting to model training and Fine-tuning.

Fine-tune SAM on custom dataset

How to Fine-Tune the SAM Model with Your Own Dataset

Fine-tuning Segment Anything (SAM) improves its accuracy for specific domains like medical imaging, agriculture, and surveillance. While SAM performs well out of the box, customizing it helps capture finer details.

Choosing The Right LLM for Your Task

Explore the right LLM for your coding or other use case. I tested ChatGPT, Claude, DeepSeek, and many more to find out which LLM performs best in a specific use case.

MistralOCR: Does It Do What It Claim?

Is MistralOCR the Best OCR Model Yet?

In this, we compare MistralOCR with similar other models in various cases to see which model performed best OCR.

YOLOv12:Is It Better At Object Detection?

object detection

YOLOv12 Real Time Object Detection: What's New?

YOLOv12 is here, faster, smarter, and more efficient. But does it truly outperform previous versions in object detection? We explore its accuracy, speed, and enhancements to see if it sets a new benchmark in AI vision.