Jiaojiao Fan

I am a Senior Research Scientist at NVIDIA Cosmos Lab in Santa Clara, California, where I work on world foundation models. Currently, I am working on improving Cosmos, NVIDIA's open-sourced groundbreaking world foundation model for Physical AI.

I completed my PhD in Machine Learning at Georgia Institute of Technology in 2024, where I was advised by Prof. Yongxin Chen. During my PhD, I was fortunate to do internships at NVIDIA research, Snap Creative Vision Research, and Microsoft Research.

CV  /  Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  X

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3 is an omnimodal foundation model that connects understanding, generation, simulation, and action through a shared world model spanning text, images, video, audio, and actions.

Cosmos 2.5: World Simulation with Video Foundation Models for Physical AI

Cosmos-Predict2.5 is a flow-based world foundation model that unifies Text2World, Image2World, and Video2World generation in a single model, using Cosmos-Reason1 for improved grounding. It is trained on 200M curated video clips and refined with reinforcement learning-based post-training.

Cosmos 1: Cosmos World Foundation Model Platform for Physical AI

NVIDIA’s open-source video world model platform for Physical AI represents a foundational breakthrough in world modeling. Cosmos enables developers to customize, and deploy world foundation models that can understand and predict physical interactions in video sequences

Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

Edify Image is a family of cascaded pixel-space diffusion text-to-image models capable of generating photorealistic images. Edify Image delivers exceptional human personalization results with remarkable identity consistency. The model also supports style transfer, 4K upsampling, ControlNets, and 360° HDR panorama generation

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance

RefDrop is a training-free method for controlling consistency in image and video generation. By manipulating attention modules in diffusion models, RefDrop enables consistent character generation, multiple subject blending, diverse content creation, and enhanced temporal consistency in videos

Variational Wasserstein Gradient Flow

A scalable approach to Wasserstein gradient flow using variational formulations

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

A novel scalable algorithm for computing Wasserstein Barycenters using Input Convex Neural Networks

Mentorship

I have had the privilege of working with or mentoring talented students and researchers.

Design and source code from Leonid Keselman's website