Kolibri
“We train Kolibri on 24T tokens across pre-training, mid-training, and long-context extension, with German accounting for more than 20% of the data mix by bytes.”
The authors, in the abstract
A Sovereign European Model on the Pareto Frontier
AI Research Radar
Monday, October 26: 1 frontier paper out of 225 read.
Frontier
Papers rated as moving the field
How we chooseThis week in research
Oct 20–26: 282 cleared, 27 frontier
- Security94
- Safety54◆ 12
- Agents36◆ 6
- Robotics22◆ 3
- 4 moreTraining, Science, Reasoning, ML21◆ 3
- Language16◆ 2
- Society16
- Inference13
- Vision10
- Security94
- 8 moreLanguage, Society, Inference, Vision, Training, Science, Reasoning, ML76◆ 6
- Safety54◆ 12
- Agents36◆ 6
- Robotics22◆ 3
Size: cleared papers◆ and tint: frontier papers
Models under test
Papers this week that name the model
Labs publishing
Papers this week with an author at the lab
Also cleared
7 papers, by field
Agents3
- DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical TasksCode
- Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations
- Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox