最有价值项目

The Solidity Smart-Contract Advisor is a cutting-edge tool designed to extend the capabilities of traditional language models in understanding and advising on Solidity smart contracts

Pytorch Implementation of CLIP-Lite | Accepted at AISTATS 2023

PegasusX: The Future of Multimodal Embeddings 🦄 🦄

A modular, multilingual, and multimodal Retrieval-Augmented Generation (RAG) system tailored for the financial analysis of Public Investment Fund (PIF) annual reports.

Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editing — externalizing visual history into episodic memory with selective retrieval. Includes the M2CA-Bench benchmark.

OpenRouter skill for AI agents: model discovery, multimodal chat, tool calling, routing, and starter templates.

It is the implementation of paper "Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model"

[NLPCC 2024] Shared Task 10: Regulating Large Language Models

Torch code for Visual Question Generation

Code for the paper [SIGIR'26]“Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling

Summit Vitals: Multi-Camera and Multi-Signal Biosensing at High Altitudes

对标蚂蚁阿福的开源大健康 AI 助手，基于 LangGraph + FastAPI + React，支持多智能体、RAG、报告解读、拍照问药与链路评估。Open-source AI health assistant inspired by Ant Afu, with multi-agent routing, RAG, multimodal medical vision, tracing, and evals.

An Interactive Game-based Vision Planning benchmark

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (ACL 2025 Main Conference)

[ICRA26] OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation

🧠🔥 Adaptive and inclusive neurotech platform for real-time multimodal data — born from the Olympic flame project.

This repository provides the code for a multimodal realistic simulation framework using CARLA and MATLAB.

[NLPCC'23] ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles PyTorch Implementation

A 5-way embedding model for text, audio, image, video, and 3D point clouds.