Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

HumanPlus: Humanoid Shadowing and Imitation from Humans

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"

🐚 OpenDevin: Code Less, Make More

Soar, a general cognitive architecture for systems that exhibit intelligent behavior.

Code for the paper "Causal Transformer for Estimating Counterfactual Outcomes"

[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

Sample code for the Microsoft Cognitive Services Speech SDK

A solver for mixed-integer nonlinear optimization problems

General reasoning component for applications based on NARS theory.

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Code for the CVPR 2023 paper "NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images".

[arXiv'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

A toolbox for mapping and localization with line features.

Gym environment for building simulation and control using reinforcement learning

A library of reinforcement learning components and agents

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Fine-tune LLM agents with online reinforcement learning

Large Action Model framework to automate browser interaction

Chat Bot with LLM and Fact Reference. Retriever Augmented Generation backed

Intrinsic Image Diffusion for Single-view Material Estimation

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

[CVPR 2024] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering

The Advanced Controls Test Bed (ACTB) is a virtual buildings test bed that interfaces external controllers to high-fidelity Spawn of EnergyPlus models.

Structured state space sequence models