Geometric Deep Learning book draft complete; Veličković calls it his most significant output in 5 years
TacoCohen · x · 2026-11-11
The full draft of the Geometric Deep Learning book is now complete, with all chapters available online from the authors' website. Co-author Petar Veličković says that while his day-to-day research moves at the pace of today's AI systems, he considers this book his most significant research output of the last five years — and still highly relevant. He is running a 'book tour' of talks extending well into 2027 and may write a blog post on the role of education in his approach to research.
Related event: Geometric Deep Learning Book Draft Completed After Five Years, Free Online(4 posts)→
More from Research
- NYU's Steertuning teaches robots chores from 5 human demos in under 5 minutes, 71% success — CyberRobooo · 2026-11-11
- NYU's Steertuning Lets a Robot Learn a Chore From 5 Minutes of Human Demo — CyberRobooo · 2026-11-11
- New preprint maps human embryonic patterning in early organogenesis at spatial single-cell resolution — anshulkundaje · 2026-11-11
- OpticalRAG compresses retrieved documents to 16 visual tokens with best compression-aware accuracy — kalyan_kpl · 2026-11-11
- Baidu's ERNIE Evolve tops public bests on NanoGPT Speedrun, brings RSI to real inference optimization — xiaohu · 2026-11-11
- Diffusion Week 2026 releases all 10 lectures on video generation, world models and more — LucaAmb · 2026-11-11