Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Mage-VL is a novel streaming multimodal foundation model that reduces visual token consumption by over 75% using a custom Mage-ViT tokenizer that selectively encodes dynamic regions via motion vectors and residual energy, and employs a dual-system architecture for real-time perception. It matches or outperforms larger models on various tasks with up to 3.5x inference speedup.
-->
[Submitted on 27 Jul 2026]
Title:Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
View a PDF of the paper titled Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model, by Senqiao Yang and 22 other authors
View PDF HTML (experimental)
Abstract:Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process them inefficiently. We present Mage-VL, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction. At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions using motion vectors and residual energy across sparse anchor (I) and predicted (P) frames. Operating at a 16 x 16 patch level, this reduces visual token consumption by over 75% while preserving spatiotemporal context. Trained from scratch on approximately 560M unlabeled images and 100M unlabeled video frames, Mage-ViT matches or outperforms flagship encoders trained on billions of image-text pairs. We establish AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes. Furthermore, through a bio-inspired dual-system architecture - a lightweight System 1 event gate and a causal System 2 decoder - Mage-VL enables proactive streaming perception. Extensive evaluations show that Mage-VL-4B matches Qwen3-VL-4B on static tasks while achieving strong gains in video understanding and 2D/3D spatial reasoning, with up to a 3.5x wall-clock inference speedup, and comprehensively surpasses the 15B Phi-4-reasoning-vision baseline. Beyond model artifacts, we deliver seven key empirical findings covering pre-training data efficiency, variable-resolution scaling, codec system acceleration, VideoQA SFT redundancy, motion-spatial synergy, AI4AI data pipelines, and Zero-Vision SFT for multimodal RL.
Comments: Project page: this https URL
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL)
Cite as: arXiv:2607.24904 [cs.CV]
(or arXiv:2607.24904v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.24904
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Senqiao Yang [view email] [v1] Mon, 27 Jul 2026 17:59:53 UTC (2,571 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model, by Senqiao Yang and 22 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-07
Change to browse by:
cs cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)