Let Joy Lead.

Create Your Infinite Interactive 3D Animated Shorts.
Building Better Social Connections and Personality Expression.

Flimo: Avatars to Stories

Flip fun Shorts in your Mood

Mockup image
Device frame
Mockup image
Device frame

Research

We are committed to the research of generative interactive AI, bringing a new experience of infinite real-time interaction to global users. These original technologies include performance agent of 3D characters, interactive 3D space generation, physical human-scene interactions, etc.

  • TokenHSI：Unified synthesis of physical human-scene interactions through task tokenization

    TokenHSI is a unified model that learns various HSI skills within a single transformer network and can flexibly generalize learned skills to novel tasks and environments through a simple yet efficient policy adaptation.
    Learn more

  • GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects

    We introduce GausSim, a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.
    Learn more

  • AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

    We introduce AnySplat, a feed‑forward network for novel‑view synthesis from uncalibrated image collections.
    Learn more

  • MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation

    MV-CoLight, a two-stage framework for illumination-consistent object compositing in both 2D images and 3D scenes.
    Learn more

  • Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation

    Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI.
    Learn more

  • Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning

    Realistic 3D indoor scene synthesis is crucial for Embodied AI and digital content creation. However, achieving high fidelity, strong generalization and precise controllability remains challenging due to complex semantic and physical constraints.
    Learn more

  • EdgeTAM: On-Device Track Anything Model

    On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for video segmentation task.
    Learn more

  • GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation

    This paper introduces a novel 3D generation framework that addresses these challenges, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space.
    Learn more

About US

Building Better Social Connections and Personality Expression. We gathered a group of people who hope to bring happiness to others.They are AI scientists, algorithm researchers, game engineers, designers, and interactive entertainment product managers. 

  • 1

    Our two founders have been working together for over 3 years at the same research institution, engaged in AIGC technology research and strategic work.

    Step illustration
  • 2

    At the end of 2024, we formed a startup team and received over $10 million in venture capital. We are all enthusiasts of gaming and content creation. 

    Step illustration
  • 3

    Up to now, dozens of papers have been published at top computer conferences (ICLR, CVPR, NeurIPS, SIGIR, ECCV, etc,) and followed by many top institutions and enterprises.

    Step illustration
  • 4

    In April 2025, we began developing a mobile application(Flimo) which your can create infinite interactive 3D animated shorts with out any skills.
    Flimo empowered by the world's first real-time generative interactive animation system(GIAS).

    Step illustration
  • 5

    We hope you like Flimo,and we will continue to release many fun features.
    The five cuties you see on the screen now are called Flimon, and they will accompany you to experience this application together!

    Step illustration

Submission Successful

The form has been successfully submitted.