Stars
😎高稳定、🧩支持扩展、🦄多模态的 ChatGPT QQ / QQ频道 / One Bot 机器人🤖 | 支持 OpenAI GPT、Dify、Claude、Gemini、gpt4free、Ollama、Gitee AI、DeepSeek、Moonshot、ChatGLM、xAI 等 LLM 的 QQ / QQ频道 / OneBot 机器人 / Agent 平台;原名 QChatGPT
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
The official implementation of IJCV & BMVC 2022 paper "One-Pot Multi-frame Denoising".
A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”
[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)
基于微博的网络舆情话题分析和用户画像系统
A python library for social event detection
This is an official PyTorch implementation for "MuSc : Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images" (MuSc ICLR2024).
Official implementation of the paper “MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体!
A Unified Parameter-Efficient Transfer Learning Benchmark for Computer Vision Tasks
A package for parsing PDFs and analyzing their content using LLMs.
Code for ICLR 2024 (Spotlight) paper "MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding"
Official Implementation of ECCV2024 paper: Chat Edit 3D: Interactive 3D Scene Editing via Text Prompts
GPT-4 level function calling models for real-world tool using use cases
"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances" (Official Implementation)
Connect agents to live web environments evaluation.
MoH: Multi-Head Attention as Mixture-of-Head Attention
This is the official code for the paper Tailor3D
This Python-based simulation platform can realistically model various components of the UAV network, including the network layer, MAC layer and physical layer, as well as the UAV mobility model, en…
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
[NeurIPS'24] "Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration"