Agentic LLM framework for conceptual systems engineering and design.

Solve Visual Understanding with Reinforced VLMs

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

code for our ICCV 2021 paper "DeepCAD: A Deep Generative Network for Computer-Aided Design Models"

[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"

Visual Instruction Tuning for Qwen2 Base Model

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models

InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

SOROTOKI is an open-source MATLAB package that includes an array of tools for design, modeling, and control of soft robotic systems 🐙 🤖