Teaching Robots to Fold Clothes: SmolVLA for Bimanual Cloth Manipulation

How a 450M-parameter Vision-Language-Action model learns to coordinate two robot arms for fabric folding — from just 50 human demonstrations.

Apr 16 • Dr Rajat Dandekar

8

Knowledge Distillation & Data-Efficient Image Transformers

The original ViT needed 300 million images to outperform CNNs. DeiT does it with just 1.2 million, by letting a CNN teacher distill its visual…

Apr 13 • Mayank Pratap Singh

15

1

TurboQuant: The Surprisingly Simple Trick That's Changing How We Compress LLMs

A first-principles walkthrough of the key idea behind Google's viral quantization paper

Apr 7 • Vizuara AI Labs

21

Attention Residuals: Teaching transformers to choose which layers matter

How Moonshot AI replaced a decade-old fixed-weight residual connection with learned depth-wise attention, unlocking 25% more compute efficiency in Kimi

Apr 6 • Naman Dwivedi

13

1

March 2026

Vision Transformers

Understanding and fine-tuning Vision Transformers (ViT) for image classification, to hands-on transfer learning with pretrained models.

Mar 22 • Mayank Pratap Singh

65

7

The Transformers

A complete architectural breakdown of Transformers, paired with a step-by-step guide to coding BERT from the ground up.

Mar 17 • Mayank Pratap Singh

156

5

19

February 2026

Diffusion Policy: Teaching Robots to Act by Denoising

How diffusion models solve the multimodal action problem in robot imitation learning

Feb 23 • Dr Rajat Dandekar

5

How to run Robotics simulations in Maniskill Environment?

Getting started with Robotics simulation environments!

Feb 8 • Dr Rajat Dandekar

5

January 2026

Segment Anything Model (SAM)

The promptable foundation model revolutionizing zero-shot image segmentation through massive-scale training.

Jan 20 • Mayank Pratap Singh and Sreedath Panat

16

3

Detection Transformer (DETR): An introduction

How to use transformer for object detection from images?

Jan 15 • Mayank Pratap Singh and Sreedath Panat

10

Why Deployment and Monitoring Are Central to Production-Grade ML Systems

This article examines the necessity of deployment, the importance of monitoring, the key components that require monitoring, and how engineers select…

Jan 14 • Prathamesh Dinesh Joshi and Vizuara AI Labs

6

3

An beginners introduction to Swin transformer

Why did Microsoft introduce the idea of "shifted window" attention?

Jan 13 • Sreedath Panat and Mayank Pratap Singh

9