Sitelet https://github.com/AIGeeksGroup
Skip to content
@AIGeeksGroup

AI Geeks

Precision beats power. Timing beats speed.
README.md

AI Geeks
Precision beats power. Timing beats speed.

Group Website LinkedIn

About

AI Geeks is a research group formed by a team of enthusiastic researchers who are passionate about cutting-edge computer vision and machine learning. The group's research spans multiple disciplines, including AI for Health, Multimodal LLM Agents, 3D Generative Modeling, and Robotics. The group continually pushes the boundaries of AI research, producing significant cross-disciplinary outputs and having papers accepted at prestigious international conferences and journals. Feel free to join us if you are interested in being part of our research or supporting us in other ways.

News

(07/30/2024) 🎉 Our paper XLIP has been highlighted by CVer!
(07/19/2024) 🎉 Our paper Motion Avatar has been accepted to BMVC 2024!
(06/18/2024) 🎉 Our paper JointViT has been selected as oral presentation at MIUA 2024!
(05/23/2024) 🎉 Our paper Motion Avatar has been highlighted by AI Bites!
(05/22/2024) 🎉 Our paper Motion Avatar has been highlighted by Language Model Digest!
(05/21/2024) 🎉 Our paper Motion Avatar has been highlighted by CSVisionPapers!
(05/14/2024) 🎉 Our paper JointViT has been accepted to MIUA 2024!
(03/02/2024) 🎉 Our paper A Deep Learning Approach to Diabetes Diagnosis has been accepted to ACIIDS 2024!
(02/10/2024) 🎉 Our paper SegReg has been accepted to ISBI 2024!
(11/16/2023) 🎉 Our paper SegReg has been highlighted by CVer!
(09/29/2023) 🎉 Our paper BHSD has been accepted to MLMI 2023!
(08/23/2023) 🎉 Our paper BHSD has been highlighted by CVer!

Research

XLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
Preprint
arXiv GitHub Papers With Code BibTeX

Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion
BMVC 2024
Website arXiv GitHub Papers With Code BibTeX

JointViT: Modeling Oxygen Saturation Levels with Joint Supervision on Long-Tailed OCTA
MIUA 2024 Oral
Website arXiv GitHub Papers With Code BibTeX

SegReg: Segmenting OARs by Registering MR Images and CT Annotations
ISBI 2024
Website arXiv OpenReview GitHub Papers With Code BibTeX

BHSD: A 3D Multi-class Brain Hemorrhage Segmentation Dataset
MLMI 2023
DOI arXiv OpenReview GitHub Kaggle Papers With Code Papers With Code BibTeX

A Deep Learning Approach to Diabetes Diagnosis
ACIIDS 2024
Website arXiv GitHub Papers With Code BibTeX

People


QIYI
Jiayu
Biao
Chen
lgx
Steve
ZeroHzzzz

Shawn
Ken
Zhiyuan
Malie
Kaiqi
Shiya
Jiamei

anan

Contact

Popular repositories Loading

  1. 3D-R1 3D-R1 Public

    [NeurIPS 2026 Reviewed (5/4/4 - A/WA/WA)] 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

    Python 417 16

  2. AnyDepth AnyDepth Public

    AnyDepth: Depth Estimation Made Easy

    Python 332 18

  3. PresentAgent PresentAgent Public

    [EMNLP 2025 Demo] PresentAgent: Multimodal Agent for Presentation Video Generation

    Python 146 14

  4. Code2Worlds Code2Worlds Public

    [ICML 2026] Code2Worlds: Empowering Coding LLMs for 4D World Generation

    Python 138 9

  5. Nav-R1 Nav-R1 Public

    Nav-R1: Reasoning and Navigation in Embodied Scenes

    Python 132 4

  6. EvoVLA EvoVLA Public

    [ECCV 2026] EvoVLA: Self-Evolving Vision-Language-Action Model

    Python 125 40

Repositories

Showing 10 of 66 repositories
  • Code2Games Public

    Code2Games: Enabling Coding Agents for Gaming World Generation

    AIGeeksGroup/Code2Games's past year of commit activity
    Python 30 2 0 0 Updated Oct 6, 2026
  • PWM Public

    PWM: Personalized World Models with Online Reinforcement Learning

    AIGeeksGroup/PWM's past year of commit activity
    Python 0 0 0 0 Updated Oct 6, 2026
  • RFPO Public

    RFPO: Rectified Flow Policy Optimization for Embodied Control

    AIGeeksGroup/RFPO's past year of commit activity
    Python 1 0 0 0 Updated Oct 4, 2026
  • DC-Scene Public

    [PRL 2026 & 3DV 2026 Exploration Edge Track] DC-Scene: Data-Centric Learning for 3D Scene Understanding

    AIGeeksGroup/DC-Scene's past year of commit activity
    Python 0 0 0 0 Updated Oct 4, 2026
  • DramaAgent Public

    [AACL-IJCNLP 2026] DramaAgent: Agentic Drama Video Generation

    AIGeeksGroup/DramaAgent's past year of commit activity
    Python 2 0 0 0 Updated Oct 4, 2026
  • HumanoidTTT Public

    HumanoidTTT: Test-Time Capability Reuse for Efficient Humanoid Control

    AIGeeksGroup/HumanoidTTT's past year of commit activity
    Python 2 0 0 0 Updated Oct 4, 2026
  • DexPolicy Public

    DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation

    AIGeeksGroup/DexPolicy's past year of commit activity
    Python 2 MIT 0 0 0 Updated Oct 4, 2026
  • DragMesh Public

    [IJCV 2026] DragMesh: Interactive 3D Generation Made Easy

    AIGeeksGroup/DragMesh's past year of commit activity
    Python 21 1 0 0 Updated Oct 2, 2026
  • DeltaWAM Public

    DeltaWAM: Delta World Action Models for Bimanual Manipulation

    AIGeeksGroup/DeltaWAM's past year of commit activity
    Python 5 1 1 1 Updated Sep 28, 2026
  • MotionVLA Public

    [NeurIPS 2026 Reviewed (5/5/4/3 - A/A/WA/WR)] MotionVLA: Vision-Language-Action Model for Humanoid Motion

    AIGeeksGroup/MotionVLA's past year of commit activity
    Python 13 0 1 0 Updated Sep 26, 2026
View all repositories

Most used topics

Loading…