Shunli Wang (王顺利)

EasyOffer. 《EasyOffer》（<大模型面经合集>）是针对LLM宝宝们量身打造的大模型暑期实习Offer指南，主要记录大模型暑期实习和秋招准备的一些常见大厂手撕代码、大厂面经经验、常见大厂思考题等；小白一个，正在学习ing......有问题各位大佬随时指正，希望大家都能拿到心仪Offer！

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

Awesome-Unified-Multimodal-Models. Awesome Unified Multimodal Models

AI-Face-FairnessBench. We introduce AI-Face, the first million-scale AI-generated face dataset with demographic annotations, and conduct a comprehensive fairness benchmark. Our work has been accepted at CVPR 2025.

SOLO. Python

Effort-AIGI-Detection. Official implementation of ICML 2025 Oral 🏆 paper "Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection".

DeepfakeBench. A comprehensive benchmark of deepfake detection

Awesome-Deepfakes-Detection. A list of tools, papers and code related to Deepfake Detection.

Awesome-AI-generated-Image-Detection. A list of awesome papers on AI-generated Image Detection.

DF40. Official repository for the next-generation deepfake detection dataset (DF40), comprising 40 distinct deepfake techniques, even the just released SoTAs. Our work has been accepted by NeurIPS 2024.

Mamba-in-CV. A paper list of some recent Mamba-based CV works.

langchain-examples. 🦜通过演示 LangChain 最具有代表性的应用范例，带你快速上手 LangChain 各个使用场景。（包含完整代码和数据集）

3D-Occupancy-Perception. [Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective

Awesome-occupancy-perception.

Awesome-BEV-Perception. Awesome-BEV-Perception

BEV-Perception. Bird's Eye View Perception

AISystem. AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Diffusion-Models-Papers-Survey-Taxonomy. Diffusion model papers, survey, and taxonomy

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

routing-transformer. Fully featured implementation of Routing Transformer

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

video-action-recognition-datasets. This repository contains video datasets that can be used for training coarse to fine-grained (phase, step and action) temporal classification tasks.

TMRNet. [TMI'2021] Temporal Memory Relation Network for Workflow Recognition from Surgical Video

coding-for-great-offer. 大厂算法和数据结构刷题班

course. 高性能并行编程与优化 - 课件

algorithm-journey. 左程云的算法和数据结构通关课

CPR-CLIP. [IEEE SPL 2023] CPR-CLIP: Multimodal Pre-training for Composite Error Recognition in CPR Training.

conv2d_direct. Cuda

DeepKE. [EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

CA-SpaceNet. [IROS 2022] CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space

DiffAct. Code for Diffusion Action Segmentation (ICCV 2023)

Video-Relation-Detection.

VideoRelationDetection2021.

LeetCode-Book. 《剑指 Offer》《图解算法数据结构》《Krahets 笔面试精选 88 题》Python, Java, C++ 解题代码

CALM. Python

KnowLM. An Open-sourced Knowledgable Large Language Model Framework.

CPR-Coach. Coach-Project

reformer-pytorch. Reformer, the efficient Transformer, in Pytorch

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

ActionCLIP. This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

pytorch-softdtw-cuda. Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

fast-transformers. Pytorch library for fast transformer implementations

TriDet. [CVPR2023] Code for the paper, TriDet: Temporal Action Detection with Relative Boundary Modeling

ms-tcn. Python

pytorch-i3d. Python

pytorch-i3d.

C2F-TCN. Official implementation of Coarse to Fine Multi-Resolution Temporal Convolutional Network for Temporal Action Segmentation

MS-TCN2. MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (TPAMI 2020)

ASFormer. Official repo for BMVC2021 paper ASFormer: Transformer for action segmentation

UVAST. Official Implementation of the paper "Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation" (ECCV 2022)

Hands-on-GEMM. Cuda

cholect50. A repository for surgical action triplet dataset. Data are videos of laparoscopic cholecystectomy that have been annotated with <instrument, verb, target> labels for every surgical fine-grained activity.

Reading-for-Surgical-Vision. Reading list and publicly available datasets for surgical vision

CUDA_Freshman. Cuda

MMNet. Python

cutlass. CUDA Templates and Python DSLs for High-Performance Linear Algebra

cuda_sgemm. Cuda

Tutorials. Parallel programming tutorials

Chinese-medical-dialogue-data. Chinese medical dialogue data 中文医疗对话数据集

MING. 明医 (MING)：中文医疗问诊大模型

alpaca-lora. Instruct-tune LLaMA on consumer hardware

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

cuda-samples. Samples for CUDA Developers which demonstrates features in CUDA Toolkit

block.bootstrap.pytorch. BLOCK (AAAI 2019), with a multimodal fusion library for deep learning models

DeepIE. DeepIE: Deep Learning for Information Extraction

GlobalPointer_torch. CMeEE/CBLUE/NER实体识别

GPLinker_torch. CMeIE/CBLUE/CHIP/实体关系抽取/SPO抽取

cnSchema. 开放中文知识图谱的schema

flownet2-pytorch. Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Train_Custom_Dataset. 标注自己的数据集，训练、评估、测试、部署自己的人工智能算法

CAM. Class Activation Mapping

action-modifiers. Code for the CVPR 2020 paper 'Action Modifiers: Learning from Adverbs in Instructional Videos'

denseflow. Extracting optical flow and frames

AggPose. [IJCAI 2022] Official PyTorch implementation of AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation

multiview_human_dataset. dataset for cvpr2020 "4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras"

YLearn. YLearn, a pun of "learn why", is a python package for causal inference

hmr-survey. [TPAMI 2023] Recovering 3D Human Mesh from Monocular Images: A Survey

video_features. Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

upt. [CVPR'22] Official PyTorch implementation for paper "Efficient Two-Stage Detection of Human–Object Interactions with a Novel Unary–Pairwise Transformer"

mmdetection. OpenMMLab Detection Toolbox and Benchmark

cuda_programming. Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

Hierarchical-Task-Modeling. Python

actseg. Action Segmentation Utilities: Evaluation and More ...

MuCon. Official Implementation for "Fast Weakly Supervised Action Segmentation Using Mutual Consistency" - TPAMI 2021

TimeSformer. The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"

awesome-public-datasets. A topic-centric list of HQ open datasets.

FineDiving. FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment

pytorch-parallel. Optimize an example model with Python, CPP, and CUDA extensions and Ring-Allreduce.

matrix-operations. some common used matrix operations (for artificial neural network model)

matrix-cuda. matrix multiplication in CUDA

step-by-step-neural-network. step-by-step, implement a neural network with python and numpy to recognize handwritten number

My-First-CUDA-Code. The introduction to cuda, a simple and easy cuda project

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Apollo-11. Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

Awesome-Temporal-Action-Localization. A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.

RTD-Action. [ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

ZeroShotVideoClassification. Zero-shot video classification by end-to-end training of 3D convolutional neural networks

BSN-boundary-sensitive-network. Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"

Bridge-Prompt. [CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

TAdaConv. [ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.