TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Fast and memory-efficient exact attention

A high-throughput and memory-efficient inference and serving engine for LLMs

Native Multimodal Models are World Learners

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Formula recognition based on LaTeX-OCR and ONNXRuntime.

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Inference script for Oasis 500M

[ICML 2025] Official PyTorch implementation of LongVU

🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

Experimented with the three essential Reinforcement Learning with Human Feedback (RLHF) process stages. It starts by revisiting the Supervised Fine-Tuning (SFT) process, then proceeds with the trai…

Evaluating text-to-image/video/3D models with VQAScore

Real-time image filter engine based on GPU

xLSTM as Generic Vision Backbone

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Deep Learning Library for Single Cell Analysis

[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

IPTV-M3U-Checker 自动化、定时、批量检测IPTV直播源.m3u的连通性与连接速度，并通过微信/钉钉群机器人以文本形式显示失效源、在线Excel预览全部检测结果。

CV算法工程师面试知识点整理

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version in translation

机器学习算法python实现

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

A Harder ImageNet Test Set (CVPR 2021)

source code for NeurIPS'23 paper "Dream the Impossible: Outlier Imagination with Diffusion Models"

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…