OpenEMMA is an open-source end-to-end multimodal model framework for autonomous driving, jointly developed by Texas A&M University, the University of Michigan, and the University of Toronto. It utilizes pre-trained large multimodal language models (MLLMs) to process visual data and complex driving scenarios...
RAG Logger is an open-source logging tool designed specifically for Retrieval Enhanced Generation (RAG) applications. As a lightweight alternative to LangSmith, it focuses on meeting the logging needs of RAG applications. RAG Logger provides query and...
GLM-Zero is an inference model from Zhipu AI based on extended reinforcement learning technology, focusing on improving the model's deep reasoning capabilities. It excels at handling mathematical logic, coding, and complex problem-solving, and has achieved success in AIME 2024, MATH500, and LiveC...
AutoRAG is a novel autonomous iterative retrieval model jointly developed by researchers from the Institute of Computing Technology/CAS (ICT/CAS), the Key Laboratory of Artificial Intelligence Security of the Chinese Academy of Sciences, and the University of Chinese Academy of Sciences. It is specifically designed for large-scale...
MARS (Market Simulation) is a financial market simulation and prediction engine developed by Microsoft Research Asia. It simulates order flows and market dynamics in financial markets based on a generative base model, the LMM (Large Market Model).
StoryWeaver is an AI model developed by the Key Laboratory of Multimedia Trusted Perception and High-Efficiency Computing of the Ministry of Education at Xiamen University and the NetEase Fuxi AI Lab. It can achieve high-quality story visualization through knowledge-enhanced story character customization...
StockMixer is a multilayer perceptron (MLP) architecture developed by Shanghai Jiao Tong University for stock price prediction, possessing both simplicity and powerful predictive capabilities. The architecture is based on three steps: indicator mixing, time mixing, and stock mixing...
LaDeCo is an automated graphic design and composition method jointly developed by Xi'an Jiaotong University and Microsoft Research. It's based on breaking down design tasks into hierarchical steps. LaDeCo performs layer planning on the input design elements, dividing them into...
SEMIKONG is a large-scale language model (LLM) specifically designed for the semiconductor industry, jointly developed by Aitomatic, FPT Software, and Tokyo Electron. Based on in-depth domain knowledge, it solves problems related to semiconductor manufacturing and design...
MinT (Mind the Time) is a multi-event video generation framework jointly developed by Snap Research, the University of Toronto, and the Vector Institute. Based on precise time control, it generates video sequences containing multiple events based on text prompts...
Wonderland, a technology developed by a research team from the University of Toronto, Snap, and UCLA, can generate high-quality, wide-range 3D scenes from a single image, allowing for control over camera trajectory. It demonstrates that 3D reconstruction models can be effectively built...
VersaGen is a generative AI agent for text-to-image synthesis, enabling flexible visual control. VersaGen can handle arbitrary combinations of elements, including single visual subjects, multiple visual subjects, and scene backgrounds...
ILLUME is a unified multimodal large-scale model proposed by Huawei Noah's Ark Lab, integrating visual understanding and generative capabilities into a single framework. The model is based on a large-scale language model (LLM) and employs a combination of continuous image input and discrete image input...
AIGCPanel is an open-source AI digital human system known for its simplicity and ease of use. It supports core functions such as video synthesis, sound synthesis, and sound cloning. Developed using TypeScript, the system is cross-platform compatible and follows the AGPL-3.0 license, facilitating...
HuatuoGPT-o1 is a complex reasoning model developed jointly by the Chinese University of Hong Kong, Shenzhen and the Shenzhen Big Data Research Institute for the medical field. It aims to improve the performance of solving medical problems based on complex reasoning capabilities. The model uses two...
LangGraph is designed for building stateful, multi-agent systems, particularly when used with large language models (LLMs) for creating agent and multi-agent workflows. As part of LangChain...
R2R is an advanced AI retrieval system focused on Retrieval-Augmented Generation. R2R integrates multimodal content ingestion, hybrid search, knowledge graph construction, GraphRAG clustering analysis, and more...
Eliza is an open-source multi-agent simulation framework developed by ai16z, designed to create, deploy, and manage autonomous AI agents. Developed in TypeScript, it provides a flexible and scalable platform for building intelligent agents...
MagicMirror is an open-source AI face-swapping, hairstyle-changing, and clothing-changing application that uses deep learning technology to allow users to transform their appearance with a single click. The application is characterized by its ease of use, hardware friendliness, privacy protection, and lightweight design, requiring no high-end hardware...
PanoDreamer is a novel method capable of generating coherent 360° 3D scenes from a single image. Unlike existing techniques, this method structures the problem as two optimization tasks: single-image panorama and depth estimation, and introduces alternating minimum...
VideoMaker is an innovative project jointly developed by Zhejiang University, Tencent, and Huawei Noah's Ark Lab. It's a zero-shot custom video generation framework based on the Video Diffusion Model (VDM). Unlike traditional methods, VideoMaker requires no additional...
TITAN is a multimodal whole-slice pathology model developed by a research team at Harvard Medical School. Through visual self-supervised learning and visual-language alignment pre-training, it can extract universal slice representations without fine-tuning or clinical labels...
TANGOFLUX is a high-efficiency text-to-audio generation model jointly developed by the Singapore University of Technology and Design (SUTD) and NVIDIA. The model boasts approximately 515 million parameters and can generate audio files up to 30 seconds long in just 3.7 seconds on a single A40 GPU...
MMedAgent is a multimodal AI agent designed specifically for the medical field, managing various medical tasks by integrating different open-source medical models. The system includes an instruction-tuned multimodal large language model (MLLM) as the action...