anniiiiiiiiiiiiiiiiiiii

[Joan Rodriguez @joanrod_ai]

The power of designing vectors through code generation, instead of approximating pixels.

Generate production-ready SVGs in the app at https://t.co/jfq6DVzwVY or through the API at https://t.co/V5Zb9PbTnJ.

[Joan Rodriguez @joanrod_ai]

Great tutorial on how to use @QuiverAI to extend vector designs while preserving your style.

Model: Arrow 1.1 Max

[Joan Rodriguez @joanrod_ai]

Mesmerizing to see @QuiverAI Arrow 1.1 turn fashion sketches into clean, editable SVGs.

It keeps the original lines, shape, and structure of the sketch.

Not just image generation. Design generation.

[anniiiiiiiiiiiiiiiiiiii @rhapsoti]

@CatorzeCat @tonialbiach

[Catorze @CatorzeCat]

Sortegem 2 lots amb 4 novel·les de Mercè Rodoreda: "La plaça del Diamant", "La mort i la primavera", "El carrer de les Camèlies" i "Jardí vora el mar".

Per participar-hi:

1. Segueix @CatorzeCat.
2. Posa un m'agrada i retuiteja-ho.
3. Etiqueta algú.
https://t.co/IeEKt4cufl

[DANN© @DannPetty]

Designers really are becoming more powerful everyday.

[AWS Startups @AWSstartups]

Joan Rodriguez shares the importance of GTM strategy when building your startup.

[Joan Rodriguez @joanrod_ai]

Welcome to the team @DannPetty 💫

Let's build the future of AI and design

[Joan Rodriguez @joanrod_ai]

One thing AI has struggled with until now: technical drawings.

@QuiverAI unlocks generating and vectorizing CAD-like visuals into clean SVG.

Powered by a shift toward visual programming.

[Joan Rodriguez @joanrod_ai]

✌️Happy Monday, back to shipping 💫

[Joan Rodriguez @joanrod_ai]

Cool use-case to try at @QuiverAI. Send a picture of you, ask it to make it a cartoon, and get it in vector-sharp format

[Joan Rodriguez @joanrod_ai]

Introducing @QuiverAI, a new AI lab and product company focused on frontier vector design.

We’ve raised an $8.3M seed round led by @a16z, with support from amazing angels and investors.

Our first model, Arrow-1.0, generates SVGs from images and text. It’s available now in public beta at https://t.co/zjAnKlI8pp

[Joan Rodriguez @joanrod_ai]

StarVector poster happening now at CVPR! Come by poster #31 if you want to chat about vector graphics, image-to-code generation, or just say hi!

[Joan Rodriguez @joanrod_ai]

The UI-Vision Benchmark is out on HuggingFace: https://t.co/80LVh2FNNC
✅Now accepted at ICML 2025.
🔥 Go test your UI Agents on the benchmark!

[Joan Rodriguez @joanrod_ai]

This is a great step toward efficient online RL! Congrats to Dima (@DBahdanau) and the team on this release. I'm excited to start using PipelineRL for multimodal use cases! 💫

[Joan Rodriguez @joanrod_ai]

Excited to be at ICLR 2025 in Singapore this week! 🇸🇬
Want to connect? Ping me!

📝 Main Conference Papers

📄 BigDocs
📅 Thu, Apr 24 | ⏰ 10:00–12:30 SGT
📍 Hall 3 + 2B | Poster #280
Open dataset for training multimodal models on document + code tasks.
🔗 https://t.co/hq3IyFRs3n

📊 InsightBench
📅 Fri, Apr 25 | ⏰ 10:00–12:30 SGT
📍 Hall 3 + 2B | Poster #306
100 real-world business datasets + AgentPoirot for multi-step analytics.
🔗 https://t.co/pohJErPBL9

📝 Workshop Papers

🧠 AlignVLM – Vision-text alignment via LLM text embeddings
📍 Re-Align Workshop | Mon, Apr 28
🔗 https://t.co/FKuM0Tp4Av

🔍 WebMMU – Benchmark for website-based multimodal understanding
🌐 VQA | Mockup2Code | Code Gen | Multilingual
📍 Deep Learning for Code Workshop | Apr 28
🔗 https://t.co/JBAx0vOBTL

Huge thanks to my coauthors + teams at @ServiceNowRSRCH and @Mila_Quebec

[Joan Rodriguez @joanrod_ai]

Following the excitement around our recent 💫 StarVector work, we're thrilled to introduce our latest research on benchmarking UI Vision Agents.

We present UI-Vision, a benchmark designed to evaluate multimodal LLMs in their UI perception, spatial reasoning, and interaction skills, with a focus on desktop GUIs and open-source applications.

🌐 Check it out: https://t.co/0IXGTEPM5k

[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 AlignVLM! We propose a new way to fuse images and text in VLMs using what we call an Align connector.

🔗 The Align connector projects vision features into a probability distribution over tokens, reusing the text embedding matrix to obtain visual tokens.

This leads to strong performance across benchmarks! Check out our deep dive 🧵

Huge congrats to the amazing multimodal team at @ServiceNowRSRCH and @Mila_Quebec

[anniiiiiiiiiiiiiiiiiiii @rhapsoti]

@Ezionavarro79 @JuanitoSay