Marco Pedersoli

[Marco Pedersoli @marcopeddy]

@PetarV_93 @gu_xiangming Also humans cannot be stochastic

[Marco Pedersoli @marcopeddy]

@francoisfleuret I fully agree. And the space of not understandable reality it's probably much larger, but we cannot see it

[Marco Pedersoli @marcopeddy]

@mihirp98 @pathak2206 @KaterinaFragiad @WuMengning54261 What about any-order autoregressive?

[Marco Pedersoli @marcopeddy]

@HeitorRapela @ICCVConference Are you still rev. 2 ? 😀

[Marco Pedersoli @marcopeddy]

@HeitorRapela @Mila_Quebec Well done. I am very interested to know about your findings!

[Gradio @Gradio]

StarVector is a multimodal vision-language model for generating SVG (Scalable Vector Graphics)

Performs image2SVG and text2SVG generation. 🤗 Gradio app is live!

The video demonstrates how image generation is treated similarly to code generation task by StarVector MVLM! 🤩

[AK @_akhaliq]

StarVector is out on Hugging Face

StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text.

It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

[Joan Rodriguez @joanrod_ai]

I’m excited to announce that 💫StarVector has been accepted at CVPR 2025! Over a year in the making, StarVector opens a new paradigm for Scalable Vector Graphics (SVG) generation by harnessing multimodal LLMs to generate SVG code that aesthetically mirrors input images and text. With this milestone, we’re also releasing StarVector on Hugging Face! 🥳🚀

[Joan Rodriguez @joanrod_ai]

🎉 Excited to introduce BigDocs!
An open, transparent multimodal dataset designed for:

📄 Documents
🌐 Web content
🖥️ GUI understanding
👨‍💻 Code generation from images

We’re also launching BigDocs-Bench, featuring 10 tasks to test models on:

➡️ Document, Web, GUI Visual reasoning
➡️ Converting images into JSON, Markdown, LaTeX, SVG, and more!

📜 Paper: https://t.co/NsXtsIennh https://t.co/EXhEFnQ622
🌍 Website https://t.co/kA9c6JH7L8

[Marco Pedersoli @marcopeddy]

@jxmnop Recurrent transformer?

[Marco Pedersoli @marcopeddy]

@RishavPramanik Thanks Rishav for your great work! It has been fun to work with you on this paper.

[Marco Pedersoli @marcopeddy]

@wellingmax Right to the point! How to avoid that?

[Marco Pedersoli @marcopeddy]

@ylecun @rmarcilhoo @erichammy @StevenLevy @DBahdanau @kchonyc @aidangomez But transformers can be trained in parallel because they do not have state vector, while lstm cannot. That's what is also making Mamba popular in these days. It can be trained in parallel because its state computation is linear over time, but its complexity for inference is fixed

[Marco Pedersoli @marcopeddy]

@_akhaliq Very impressive!

[Marco Pedersoli @marcopeddy]

@_akhaliq I really think this is the way to go for LLM

[Marco Pedersoli @marcopeddy]

@_akhaliq Isn't this just ensembling?

[Joan Rodriguez @joanrod_ai]

Thanks @_akhaliq for sharing our work! We introduce StarVector💫 a Large Language and Vision Model for generating SVG code, a new alternative to image vectorization!

https://t.co/L55kaKJzyA

w/ @shubhamag1992, @ILaradji, @prlz77, @dvazquezcv, @chrisjpal and @marcopeddy

🧵👇

[Marco Pedersoli @marcopeddy]

@saypramoun @IsmailBenAyed1 @dvazquezcv @ILaradji Thanks Saypra, it has been a pleasure to work with you!

[Marco Pedersoli @marcopeddy]

@tunguz It does not look good for Europe :(

[Marco Pedersoli @marcopeddy]

@phillip_isola Yes, but it is using millions of images used by the pre-trained Imagen model.