Cherryjingyao

VLN-GOAT

Repository for Vision-and-Language Navigation via Causal Learning (Accepted by CVPR 2024)

Dream2Real

[ICRA 2024] Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models

e2map

accelerated_features

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

NaviLLM

[CVPR 2024] The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'

PHC

Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

PULSE

Official Implementation of the ICLR 2024 spotlight paper: Universal Humanoid Motion Representations for Physics-Based Control

InstructNav

Qwen2.5

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

visualnav-transformer

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

SuperPrompt

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

Qwen-Agent

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Qwen2-VL

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

JARVIS-1

JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models

Agent-Smith

[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

awesome-large-multimodal-agents

visualwebarena

VisualWebArena is a benchmark for multimodal agents.

Multi-Agent-GPT

Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。

Chatglm_lora_multi-gpu

chatglm多gpu用deepspeed和

alfworld

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

TaskMatrix

FireAct

FireAct: Toward Language Agent Fine-tuning

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

autogen

A programming framework for agentic AI 🤖

agentUniverse

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

Sibyl-System

mem0

The Memory layer for your AI apps

Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.