From Doodle to Design: Sketch‑to‑Layout Made Simple

Kari Jaaskelainen

04 Nov 2025 — 1 min read

From doodle to design

Imagine sketching a rough poster layout and instantly getting a polished version. That’s the promise of Sketch‑to‑Layout, a new approach that uses your sketch as the design guide.

How it works: A multimodal transformer takes your quick sketch plus content (text/images) and generates clean layouts for posters, documents, or slides.
Why it’s better: No complex constraints—sketches are intuitive, fast, and closer to how designers think.
Training breakthrough: Human sketches are scarce, so the team created ~200k synthetic training sketches at scale.
Results: Outperforms state-of-the-art constraint-based methods on PubLayNet, DocLayNet, and SlidesVQA.
For the community: Paper: http://arxiv.org/abs/2510.27632v1 • Datasets: https://github.com/google-deepmind/sketch_to_layout

This work establishes "sketch-to-layout" as a promising direction for making AI design tools more usable and creative.

Paper: http://arxiv.org/abs/2510.27632v1

Register: https://www.AiFeta.com

AI Design GenerativeAI UX ComputerVision OpenSource Layout Creativity Research DeepLearning

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

From doodle to design

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)