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
- 2041
- Concepts
- 54
- Last filed
- Nov 13
Latest activity
- tweet Disabling thinking and exposing deep_think as a tool leaks the internal CoT reasoning format
- blog TwIL-8B — 8.8B Reasoning Model Post-Trained from Granite 4.2 with SFT + GRPO/DAPO RL
- arxiv Rethinking Activation Functions: Reducing Bias Can Improve Learning
- arxiv Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining
- arxiv Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs
- arxiv Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
- concept Inference-Time Scaling
- concept LLM Inference Efficiency
- concept Open foundation-model releases
- concept Reasoning RL