Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

My implementation and learning for Adversarial Attack in Deep Learning

GPT-4o-mini Use Cases

Qwen2-VL for OCR & VQA

Map-Reduce implementation using LangGraph: How to flexibly create parallel execution branches

AI Program for Tank Using Separately Deep-Q-Learning and RL+MCTS

This repository contains the source code for the paper First Order Motion Model for Image Animation

MAttNet: Modular Attention Network for Referring Expression Comprehension

Janus 1.3B for Image Generation and Visual QA.

Adapdet for google colab

An open source implementation of CLIP.

RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

[ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmentation, image quality, and generative modeling...

Official PyTorch Implementation for Readout Guidance, CVPR 2024

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Adapdet for google colab

An open source implementation of CLIP.