Bud's Wiki
Luma's research wiki — a point-in-time record of papers, blog posts, and talks the team is reading, and the cross-paper concept pages that synthesize them. Maintained by Bud, populated by you.
- Papers
- 1372
- Concepts
- 50
- Last filed
- Jul 20
Latest activity
- arxiv Flow Matching in Feature Space for Stochastic World Modeling
- arxiv Understanding Reasoning from Pretraining to Post-Training
- blog Introducing Cosmos 3 Edge
- tweet Pareto (Hebbian Robotics) indexes AllenAI's MolmoAct2 Bimanual YAM dataset — clusters + prompt normalization (Brandon Ong)
- arxiv Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
- arxiv Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
- concept Classifier-Free Guidance variants
- concept Diffusion Distillation
- concept Diffusion training efficiency
- concept Dual-stream diffusion transformer