Vishal

Home of FastFlexQwen aka DFQ VLA.

contains implementation and artifacts of VQ-VAE built upon NVDIA's PhysicalAI AV dataset

This repository contains the implementation of AlignVLM paper, which proposes a novel method for vision language alignment

This repo integrates DyCoke's token compression method with VLMs such as Gemma3 and InternVL3

This projects implements a toy-example of GPT-2 with additional bells and whistles like Mixture-of-Experts and MAMBA blocks.

Training (nano) DepthPro with knowledge distillation

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

This repo contains lecture notes and assignments of stanford's CS224N course of NLP

This projects implements LoRA/QLoRA to finetune Llama3 from scratch

A project aimed at understanding components of LLM tokenizers

This repository contains all the completed projects of SFND with Udacity

This repository contains the code to hide the faces from video with emojies

Repository containing work done while taking hands on lessons of Deep learning

This repository contains the implementation of CV algorithms in C++

Employed motion detection for pi-cam based surveillance

This repository contains lane detection project from Udacity's Self driving car nanodegree

Employed Transfer Learning for instance segmentation using Mask RCNN

Employed Transfer Learning for performing web-cam based object detection

Contains code for recognizing license plate characters from Images

Traffic Sign classifier based on TensorFLow

PyTorch practice notebooks from various sources

pure tensorflow Implement of YOLOv3 with support to train your own dataset

No description provided.