Align model card with GitHub repo (arXiv, project page, demo, TODO, Apache-2.0)

README.md

@@ -1,16 +1,17 @@
 ---
-license: other
+license: apache-2.0
 language:
 - multilingual
-pipeline_tag: image-text-to-text
+pipeline_tag: any-to-any
 tags:
+- any-to-any
 - hunyuan
 - hunyuan_vl_mot
 - unified_mot
 - vision-language
 - Embodied
+- image-text-to-text
 - image-to-text
-- any-to-any
 - MoT
 - flow-matching
 ---
@@ -18,11 +19,14 @@ tags:
 <div align="center">
 <h1>RxBrain</h1>
 <p><b>Embodied Cognition Foundation Model with Joint Language–Visual Reasoning and Imagination</b></p>
-<p><i>Tencent Robotics X × Futian Laboratory × Tencent Hunyuan</i></p>
+<p><i>Tencent Robotics X × Futian Laboratory × Tencent Hy Team</i></p>
 
-<a href="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/assets/RxBrain_v0.pdf"><img src="https://img.shields.io/badge/Paper-Report-red?logo=adobeacrobatreader" alt="Tech Report"></a>
-<a href="https://huggingface.co/tencent/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/Models-HuggingFace-yellow?logo=huggingface" alt="Models"></a>
-<a href="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/GitHub-Repo-181717?logo=github&logoColor=white" alt="GitHub"></a>
+<a href="https://arxiv.org/abs/2607.14187"><img src="https://img.shields.io/badge/arXiv-2607.14187-b31b1b.svg" alt="arXiv"></a>
+<a href="https://huggingface.co/tencent/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/🤗%20HuggingFace-Model-FFD21E" alt="Model"></a>
+<a href="https://tairos.tencent.com/openSourceModels/hy-embodied-rxbrain-1.0"><img src="https://img.shields.io/badge/🌐%20Project-Page-2ea44f" alt="Project Page"></a>
+<a href="https://huggingface.co/spaces/hugging-apps/rxbrain-embodied-cognition"><img src="https://img.shields.io/badge/🤗%20HuggingFace-Demo-FFD21E" alt="Demo"></a>
+<a href="https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0"><img src="https://img.shields.io/badge/GitHub-Code-181717?logo=github&logoColor=white" alt="GitHub"></a>
+<a href="./LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"></a>
 
 </div>
 
@@ -54,12 +58,11 @@ These capabilities are unified through **interleaved generation**: within a sing
   * 🎨 **Flow-Matching Image Head:** Imagined frames are produced by a flow-matching head decoding into a frozen **FLUX** VAE latent space, enabling text-to-image, multi-frame world-model rollout, and goal-image planning.
   * 🔗 **Interleaved Reasoning + Imagination:** Text reasoning and generated frames are emitted in one sequence, coupling symbolic plans with visual goals.
 
-## 📅 Roadmap
+## 📋 TODO
 
-- [x] Transformers Inference (understanding + generation)
-- [ ] vLLM Inference
-- [ ] Fine-tuning Code
-- [ ] Online Gradio Demo
+* [ ] Open-source **RxBrain-Bench**, a comprehensive benchmark for embodied cognition.
+* [ ] Open-source the fine-tuning code for **Visual Question Answering (VQA)**, **Multi Frames Generation**, and **Interleave Generation**.
+* [x] Release the **technical report**, **inference code**, and **model weights**.
 
 ## 🛠️ Dependencies and Installation
 
@@ -196,5 +199,5 @@ python interleave_inference.py \
 
 ## 📊 Evaluation
 
-RxBrain is evaluated on embodied understanding, spatial reasoning, and imagination/generation benchmarks. For detailed metrics and methodology, please refer to our [technical report](https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0/blob/main/assets/RxBrain_v0.pdf).
+RxBrain is evaluated on embodied understanding, spatial reasoning, and imagination/generation benchmarks. For detailed metrics and methodology, please refer to our [technical report](https://arxiv.org/abs/2607.14187).