No fortress, purely open ground. OpenManus is Coming.

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

A simple yet powerful agent framework that delivers with open-source models

复现大模型相关算法及一些学习记录

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

A Framework of Small-scale Large Multimodal Models

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Official implementation of project Honeybee (CVPR 2024)

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

Code for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024

The official PyTorch code for 'DER: Dynamically Expandable Representation for Class Incremental Learning' accepted by CVPR2021

Repository with the code of the paper: A proposal for Multimodal Emotion Recognition using auraltransformers and Action Units on RAVDESS dataset

[ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models

[IJCAI 2024] Continual Multimodal Knowledge Graph Construction

A Benchmark for Anytime Person Re-Identification (AT-ReID), which aims to retrieve a person at any time, including both daytime and nighttime, ranging from short-term to long-term.

A convolution neural network with SE block and haar wavelet block for Chinese calligraphy styles classification by TensorFlow.(Paper: A novel CNN structure for fine-grained classification of Chines…

VQACL: A Novel Visual Question Answering Continual Learning Setting (CVPR'23)

[AAAI2023] Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task (Oral)

An approach to utomatically generating browser environment with verifiable tasks

A Framework for Evaluating AI Agent Safety in Realistic Environments

Official implementation of the "Multimodal Parameter-Efficient Few-Shot Class Incremental Learning" paper

Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents"

Official Implementation for MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering

6th CLVISION workshop at ICCV 2025: repo for the challenge