Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！

Minimal reproduction of DeepSeek R1-Zero

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official repository for our work on micro-budget training of large-scale diffusion models.

Open and efficient video and image watermarking

A detailed formulae explanation on gaussian splatting

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

Official implementations of CIRKD: Cross-Image Relational Knowledge Distillation for Semantic Segmentation and implementations on Cityscapes, ADE20K, COCO-Stuff., Pascal VOC and CamVid.

Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.

A package to make do Network Slimming a little easier

[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

A collection of loss functions for medical image segmentation

Implementation of Hausdorff loss function for DNN learning in segmentation tasks.

A curated list of neural network pruning resources.

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

PaddleSlim is an open-source library for deep model compression and architecture search.

DataLoader subclass for PyTorch to work with HDF5 files.

[AAAI 2021] Pytorch implementation for "Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters."

Google Brain AutoML

PyTorch implementation of EfficientNetV2 family