shengyuhao

shengyuhao's Stars

• microsoft/graphrag

  A modular graph-based Retrieval-Augmented Generation (RAG) system

  Language:Python17.7k1124681.7k

• facebookresearch/segment-anything-2

  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

  Language:Jupyter Notebook11.1k64259944

• lllyasviel/Omost

  Your image is almost there!

  Language:Python7.2k4578418

• MasterBin-IIAU/UNINEXT

  [CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

  Language:Python1.5k9956158

• colmap/glomap

  GLOMAP - Global Structured-from-Motion Revisited

  Language:C++1.3k227680

• openvla/openvla

  OpenVLA: An open-source vision-language-action model for robotic manipulation.

  Language:Python1.1k1799138

• MasterBin-IIAU/Unicorn

  [ECCV'22 Oral] Towards Grand Unification of Object Tracking

  Language:Python948204587

• UMass-Foundation-Model/3D-LLM

  Code for 3D-LLM: Injecting the 3D World into Large Language Models

  Language:Python915166255

• nianticlabs/acezero

  [ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

  Language:Python609582334

• microsoft/psi

  Platform for Situated Intelligence

  Language:C#5383717796

• NVlabs/EAGLE

  EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

  Language:Python507311643

• OpenDriveLab/Vista

  [NeurIPS 2024] A Generalizable World Model for Autonomous Driving

  Language:Python500193633

• OpenRobotLab/GRUtopia

  GRUtopia: Dream General Robots in a City at Scale

  Language:Python472111922

• StanfordVL/OmniGibson

  OmniGibson: a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse engine. Join our Discord for support: https://discord.gg/bccR5vGFEx

  Language:Python4622144550

• UMass-Foundation-Model/3D-VLA

  [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

  Language:Python32318611

• facebookresearch/open-eqa

  OpenEQA Embodied Question Answering in the Era of Foundation Models

  Language:Jupyter Notebook20791019

• scene-verse/SceneVerse

  Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"

  Language:Python17211222

• Chat-3D/Chat-Scene

  A multi-modal large language model for 3D scene understanding, excelling in tasks such as 3D grounding, captioning, and question answering.

  Language:Python808406

• invictus717/MiCo

  Explore the Limits of Omni-modal Pretraining at Scale

  Language:Python80284

• OpenRobotLab/Grounded_3D-LLM

  Code&Data for Grounded 3D-LLM with Referent Tokens

  Language:Python78681

• clorislili/ManipLLM

  The official codebase for ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation(cvpr 2024)

  Language:Python72364

• ZCMax/ScanReason

  [ECCV 2024] Empowering 3D Visual Grounding with Reasoning Capabilities

  Language:Python45331

• JudyYe/diffhoi

  Language:Jupyter Notebook24130

• alanaai/EVUD

  Egocentric Video Understanding Dataset (EVUD)

  Language:Python19312

• eric-ai-lab/MMWorld

  Official repo of the paper "MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos"

  Language:Python19211

• showlab/videogui

  official repo of "VideoGUI: A Benchmark for GUI Automation from Instructional Videos"

  Language:JavaScript19300

• Nathan-Li123/LaMOT

  163

• BolinLai/LEGO

  [ECCV2024, Oral]This is the official implementation of the paper "LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning".

  Language:Python8100

• PKU-ICST-MIPL/FineSports_CVPR2024

  723

• taeinkwon/PyHoloAssist

  Language:Python3101