From c16578d437e12b891dab2999919b3e1e9b9536dd Mon Sep 17 00:00:00 2001
From: Sophia Huang <hhuang@berkeley.edu>
Date: Thu, 5 Jun 2025 17:18:37 -0700
Subject: [PATCH] Update README.md

---
 README.md | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index bf3c75a..c044366 100644
--- a/README.md
+++ b/README.md
@@ -1,18 +1,29 @@
 <p align="center">
-    <img src="assets/nvidia-cosmos-header.png" alt="NVIDIA Cosmos Header">
+    <span style="font-size: 18px;">New GitHub page for NVIDIA Cosmos: <b><a href="https://github.com/nvidia-cosmos">https://github.com/nvidia-cosmos</a></b></span>
 </p>
 
-Thank you all for the valuable feedback! We have restructured the codebase to make it easier to use and contribute to.
+# Nvidia Cosmos
+
+Cosmos World Foundation Models come in three model types which can all be customized in post-training: [cosmos-predict](https://github.com/nvidia-cosmos/cosmos-predict1), [cosmos-transfer](https://github.com/nvidia-cosmos/cosmos-transfer1), and [cosmos-reason](https://github.com/nvidia-cosmos/cosmos-reason1):
+
+|  | Predict | Transfer | Reason |
+| ----- | :---: | :---: | :---: |
+| **Type** | World Generation | Multi-Controlnet | Reasoning VLM |
+| **Function** | Predict novel future frames given initial frames  | Transfer existing control frames into photoreal frames within a video clip | Reason against frames within a video clip |
+| **Use Cases** | Data Generation & Policy Evaluation | Data Augmentation | Data Curation |
+| **Inputs** | Text, Image, Video  | Multiple Video Modalities such as RGB, Depth, Segmentation, and more. | Video & Text |
+| **Outputs** | Video | Video | Text  |
+
+# 
+
+# Use Cases in Physical AI Development
+
+Our world foundation models are purpose-built to accelerate improving performance in downstream model tasks in various stages, as illustrated here in the flywheel.
 
 <p align="center">
-    <span style="font-size: 18px;">New GitHub page for NVIDIA Cosmos: <b><a href="https://github.com/nvidia-cosmos">https://github.com/nvidia-cosmos</a></b></span>
+  <img src="https://raw.githubusercontent.com/nvidia-cosmos/cosmos-transfer1/main/assets/DataFlywheel.jpg" alt="NVIDIA Cosmos Data Flywheel">
 </p>
 
-NVIDIA Cosmos now includes three subprojects:
-
-1. [Cosmos-Predict1](https://github.com/nvidia-cosmos/cosmos-predict1) is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
-2. [Cosmos-Transfer1](https://github.com/nvidia-cosmos/cosmos-transfer1) is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
-3. [Cosmos-Reason1](https://github.com/nvidia-cosmos/cosmos-reason1) models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
 
 -----------------------------------------------------------