README: sync System-level speed metric and tech-report badge with source

README.md

@@ -14,7 +14,7 @@ tags:
 <h1 align="center">Mage-Flow<br><span style="font-size: 0.55em; font-weight: normal;">An Efficient Native-Resolution Foundation Model for Image Generation and Editing</span></h1>
 
 <p align="center">
-  <a href="https://arxiv.org/abs/2607.19064"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--Flow-b31b1b" height="22" /></a>
+  <a href="https://github.com/microsoft/Mage/blob/main/assets/mage_flow_tech_report.pdf"><img alt="Tech Report" src="https://img.shields.io/badge/arXiv-Mage--Flow-b31b1b" height="22" /></a>
   <a href="https://microsoft.github.io/Mage"><img alt="Project Page" src="https://img.shields.io/badge/%F0%9F%8C%90-Project%20Page-blue" height="22" /></a>
   <a href="https://github.com/microsoft/Mage"><img src="https://img.shields.io/badge/Code-GitHub-181717?logo=github" alt="GitHub"></a>
   <a href="https://huggingface.co/microsoft/Mage-Flow-Base"><img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--Flow--Base-yellow" height="22" /></a>
@@ -55,7 +55,7 @@ Together with native-resolution packing and a fused-kernel training infrastructu
 - **Compact & competitive.** A single 4B family for generation *and* editing that matches or beats much larger open systems (Qwen-Image 20B, Z-Image 6B, FLUX.2 32B, FireRed-Image-Edit 20B).
 - **Efficient tokenizer.** Mage-VAE matches FLUX.2-VAE reconstruction fidelity while using **~12× / ~22× fewer encode / decode MACs per pixel**, removing the VAE as the high-resolution bottleneck.
 - **Native resolution.** One checkpoint generates from **512 to 2048** on any aspect ratio, including extreme **4:1** (e.g. `512×2048`, `2048×512`).
-- **System-level speed.** Native-resolution packing (FlashAttention var-len + per-sample 2D RoPE) + fused CUDA kernels raise MFU from **~33% → ~77%** (**~2.5× faster training**); CFG's conditional/unconditional branches run in **one** packed forward.
+- **System-level speed.** Native-resolution packing (FlashAttention var-len + per-sample 2D RoPE) + fused CUDA kernels cut per-step training time from **~1.93 s → ~0.78 s** (**~2.5× faster training**); CFG's conditional/unconditional branches run in **one** packed forward.
 - **Full family.** **Base**, **RL-aligned**, and **4-step Turbo** variants for both generation and editing.
 - **Versatile editing.** Mage-Flow-Edit supports semantic content editing, appearance transformation, image restoration, and structure-aware outputs within a unified image-and-text-conditioned model. See the report's editing galleries.
 - **Interactive latency.** At `1024²` on a single A100: **Mage-Flow-Turbo 0.59 s/image**, **Mage-Flow-Edit-Turbo 1.02 s/edit**, peak memory **~18–20 GB** (lowest among compared systems).