ICML Weight-Space Symmetries keynote slides survey weight-space learning
orvieto_antonio · x · 2026-11-05
Damian Borth shared his keynote slides from the ICML Workshop on Weight-Space Symmetries, surveying "weight-space programming": treating neural network weights as a novel modality. The slides map the field's method families — encoder-only, decoder-only (INR/RNN), autoencoders, and equivariant/GNN models — with a large comparison table.
Related event: ICML Keynote Proposes "Weight-Space Learning" as New ML Paradigm(2 posts)→
More from Research
- HyperQ adds trainable quantum residual branches to a frozen 1.1B diffusion LM — jiqizhixin · 2026-11-05
- Open-source PageIndex ditches vectors for tree-search RAG, scores 98.7% on FinanceBench vs GPT-4o's 31% — aakashgupta · 2026-11-05
- Andriy Burkov releases 'The Hundred-Page Language Models Book', a hands-on PyTorch guide — burkov · 2026-11-05
- Blogger proposes scrapping ML conference checklists now that everyone uses LLMs to vet papers — bremen79 · 2026-11-05
- Agent harnesses aren't dying: harness distillation changes the job, says O'Reilly — bibryam · 2026-11-05
- VAMOS hierarchical VLA lets a robot self-navigate 2.35 km through Zurich — KyleMorgenstein · 2026-11-05