Geometric Deep Learning authors seek errata and exercise proposals as book wraps up
PetarV_93 · x · 2026-11-10
A follow-up tweet from Petar Veličković expressing disbelief that the Geometric Deep Learning book draft is done after 5+ years of work. The authors still welcome errata, comments, questions and exercise proposals, and will credit any suggestion that leads to a modification of the online text in the acknowledgements.
Supplementary to the main announcement.
Related event: Geometric Deep Learning Book Draft Completed After Five Years, Free Online(2 posts)→
More from Research
- JEPA is just a new name for old tricks: iBOT, data2vec and even CPC were basically I-JEPA — TimDarcet · 2026-11-10
- Reframe: NJU's Two-Stage Post-Training Framework Aligns Visual Agents' Observations, Beats Mix-RL and Vanilla MOPD — NJU · 2026-11-10
- Spatial Harness Grounds VLM Spatial Reasoning in Executable Physics-Engine World States — TMLR-Group-HF · 2026-11-10
- InstantHMR Runs Real-Time 3D Human Mesh Recovery on Phone NPUs: 5.5ms per Person, 12x Faster Than Peers — naturalpad · 2026-11-10
- 360-trial benchmark finds code knowledge graphs give coding agents no clear accuracy gain — JeremyCMorgan · 2026-11-10
- banteg launches a live Sokoban eval for LLMs — banteg · 2026-11-10