docs: update citation (yang2026mage, arXiv:2607.24904)

README.md

@@ -14,7 +14,7 @@ tags:
 
 <p align="center">
   <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://arxiv.org/abs/2607.24904"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--VL-b31b1b" height="22" /></a>
+  <a href="https://github.com/microsoft/Mage/blob/main/assets/mage_vl_tech_report.pdf"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-Mage--VL-b31b1b" height="22" /></a>
   <a href="https://github.com/microsoft/Mage"><img src="https://img.shields.io/badge/Code-GitHub-181717?logo=github" alt="GitHub" height="22"></a>
   <a href="https://huggingface.co/microsoft/Mage-VL"><img alt="Mage-VL" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--VL-yellow" height="22" /></a>
   <a href="https://huggingface.co/microsoft/Mage-ViT"><img alt="Mage-ViT" src="https://img.shields.io/badge/%F0%9F%A4%97-Mage--ViT-yellow" height="22" /></a>
@@ -40,6 +40,7 @@ On top of this pair, a **System 1 & System 2 dual-process design** adds proactiv
 
 - **Codec-native & from scratch.** The entire visual stack is trained from scratch — no billion-scale image-text ViT initialization. The bio-inspired predictive-patch mechanism (I/P frames at `16×16`) cuts visual-token consumption by **over 75%** (**~1/8 or less** of dense frame sampling), letting the model train on videos **8× longer** under the same budget.
 - **Codec-native speedup.** Codec tokenization sets a superior accuracy–efficiency frontier — **up to 3.5× wall-clock inference speedup** over uniform frame sampling at matched accuracy, and the fastest of all compared models on most video benchmarks (single 8×B200 node).
+- **Data-efficient tokenizer.** Trained on only **~100M unlabeled images/videos**, Mage-ViT matches or beats frontier encoders trained on billions of image-text pairs (SigLIP2 @ 10B, MoonViT @ 2B) — e.g. **99.33% on CIFAR-10** and **85.69% on ImageNet** with 256 tokens, showing web-scale pretraining is *not* essential for a strong VLM front-end.
 - **Native-resolution scaling.** Variable-resolution pretraining lets Mage-ViT improve *monotonically* with the token budget (peaking **>96.1% Food-101 / >86.3% ImageNet** at 676 tokens) where fixed-resolution encoders saturate or degrade.
 - **Matched-LLM video gains.** With the 4B Qwen3 backbone held fixed and only the ViT swapped, Mage-VL improves over Qwen3-VL-4B on **every** reported video and temporal-grounding benchmark — largest on localization-heavy tasks (**+22.5 QVHighlight**, +17.1 ActivityNet, +11.0 VSI-Bench, +24.5 VideoEval-Pro).
 - **Strong for its size.** On par with Qwen3-VL-4B on static images, and clearly ahead on video understanding and spatial intelligence (**+11.0** VSI-Bench, **+53.1** CrossPoint, **+5.2** EmbSpatial, **+22.5** QVHighlight).
@@ -49,7 +50,7 @@ On top of this pair, a **System 1 & System 2 dual-process design** adds proactiv
 
 A **single checkpoint**, `microsoft/Mage-VL`, is one unified model that **simultaneously** provides image & video understanding **and** the proactive streaming gate — the same weights answer offline image/video questions and drive event-gated commentary. It covers every Mage-VL capability: image understanding, frame-sampled video, traditional H.264/HEVC codec video, neural DCVC-RT codec video, and event-gated streaming. The repository bundles the codec processor, the neural codec package, and the proactive gate weights — no separate understanding, NVC, or streaming checkpoint is required.
 
-We additionally release **`microsoft/Mage-ViT`** — the standalone visual encoder from the two-stage, from-scratch ViT pre-training. This is the **ViT-pre-trained checkpoint only**: it has **not** gone through the joint VLM training with the language model. Use it as a data-efficient, codec-native visual encoder or as a drop-in ViT for your own multimodal training.
+We additionally release **`microsoft/Mage-ViT`** — the standalone visual encoder from the two-stage, from-scratch ViT pre-training (cluster-discrimination on ~100M unlabeled image/video frames). This is the **ViT-pre-trained checkpoint only**: it has **not** gone through the joint VLM training with the language model. Use it as a data-efficient, codec-native visual encoder or as a drop-in ViT for your own multimodal training.
 
 | Model | Task | Backbone | Hugging Face |
 | :--- | :--- | :--- | :--- |
@@ -187,7 +188,7 @@ JoyAI's high TriggerAcc comes from predicting silence almost everywhere under So
 
 Beyond the model, the report distills **seven empirical findings** for efficient multimodal training:
 
-1. **Data-efficient tokenizer.** Mage-ViT trains on only **560M unlabeled images + 100M video frames**, yet matches SigLIP2 pretrained on billions of image-text pairs.
+1. **Web-scale pretraining is not essential.** A from-scratch backbone on ~100M unlabeled frames matches encoders trained on billions of image-text pairs.
 2. **Variable-resolution pretraining scales monotonically.** Quality keeps improving with the visual-token budget instead of saturating/degrading like fixed-resolution encoders.
 3. **Codec-native tokenization sets a better accuracy–efficiency frontier** — up to **3.5× wall-clock inference speedup** over uniform frame sampling.
 4. **Explicit VideoQA SFT is redundant.** Dense video *captions* + standard image SFT are sufficient for strong zero-shot VideoQA.
@@ -219,84 +220,6 @@ pip install "transformers>=5.7" accelerate pillow torch torchvision \
 
 Codec-based video inference also requires `ffmpeg` and `ffprobe` on `PATH`.
 
-### Using 🤗 Transformers directly
-
-Mage-VL ships its modeling, processing, and chat-template code inside this repository, so image and frame-sampled video inference need **no script download and no extra package** beyond `transformers`:
-
-```python
-import torch
-from PIL import Image
-from transformers import AutoModelForCausalLM, AutoProcessor
-
-model_id = "microsoft/Mage-VL"
-processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, trust_remote_code=True, torch_dtype="auto", device_map="auto"
-).eval()
-
-messages = [{"role": "user", "content": [
-    {"type": "image"},
-    {"type": "text", "text": "Describe this image in detail."},
-]}]
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-
-inputs = processor(
-    text=[text], images=[Image.open("examples/dog.jpg").convert("RGB")], return_tensors="pt"
-)
-inputs = {k: (v.to(model.device) if hasattr(v, "to") else v) for k, v in inputs.items()}
-inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
-
-with torch.inference_mode():
-    output = model.generate(**inputs, max_new_tokens=256, do_sample=False)
-print(processor.tokenizer.decode(
-    output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True
-).strip())
-```
-
-> The image depicts a dog sitting on a patterned rug. The dog appears to be a
-> medium-sized breed with a thick, fluffy coat. Its fur is primarily white with
-> patches of black and brown. The dog's ears are perked up, and it has a calm and
-> attentive expression. [...]
-
-For video, use `{"type": "video"}` in the message and pass a list of PIL frames as `videos=[frames]`:
-
-```python
-import cv2
-import numpy as np
-from PIL import Image
-
-def sample_video(path, num_frames=32):
-    capture = cv2.VideoCapture(path)
-    total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
-    frames = []
-    for index in np.linspace(0, total - 1, min(num_frames, total), dtype=int):
-        capture.set(cv2.CAP_PROP_POS_FRAMES, int(index))
-        ok, frame = capture.read()
-        if ok:
-            frames.append(Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)))
-    capture.release()
-    return frames
-
-messages = [{"role": "user", "content": [
-    {"type": "video"},
-    {"type": "text", "text": "Describe this video."},
-]}]
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-
-inputs = processor(
-    text=[text],
-    videos=[sample_video("examples/soccer-broadcast.mp4", 32)],
-    return_tensors="pt",
-    padding=True,
-)
-```
-
-> The video opens with a man in a black polo shirt, sporting a short haircut,
-> standing in a stadium. He is holding a yellow microphone with the BBC Sport
-> logo on it. The background reveals a large crowd of spectators. [...]
-
-Add `attn_implementation="sdpa"` to `from_pretrained` if `flash-attn` is not installed. Codec-based video (H.264/HEVC, DCVC-RT) and streaming commentary use [`inference.py`](inference.py) below.
-
 ### Examples
 
 Two sample inputs ship with this repository:
@@ -413,9 +336,9 @@ The gate is trained on codec inputs, so `--video_backend codec` is the intended
 ## 📝 Citation
 
 ```bibtex
-@article{mage2026magevl,
+@article{yang2026mage,
   title={Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model},
-  author={Yang, Senqiao and Zhang, Kaichen and Jia, Zhaoyang and Guo, Jinghao and Shen, Yifei and Zhang, Xinjie and Zhang, Xiaoyi and Wang, Haoqing and Li, Xiao and An, Xiang and Xie, Yin and Liu, Zhening and Guo, Xun and Li, Jiahao and Zheng, Shicheng and Wang, Jinglu and Guo, Zongyu and Xie, Wenxuan and Zheng, Zihan and Luo, Yuxuan and Li, Bin and Lu, Yan},
+  author={Yang, Senqiao and Zhang, Kaichen and Jia, Zhaoyang and Guo, Jinghao and Shen, Yifei and Zhang, Xinjie and Zhang, Xiaoyi and Wang, Haoqing and Li, Xiao and Zhang, Peng and others},
   journal={arXiv preprint arXiv:2607.24904},
   year={2026}
 }