cd/entity/MathCAMPS· home› entities› MathCAMPS
grep -l @mathcamps /news/*.json | wc -l → 3

MathCAMPS

mentions 3 type Organization feed RSS

// recent coverage 3 mentions

17:09
2026-08-16
sourcefeed.dev
artificial-intelligence

Fine-Tuning Can't Teach What Pretraining Never Saw

Researchers at the Max Planck Institute for Intelligent Systems, ELLIS Tübingen, and ETH Zürich built LittleLearner, a 5B-parameter language model pretrained exclusively on 88 billion tokens of U.S. e…

09:08
2026-08-16
sourcefeed.dev
artificial-intelligence

Pretraining Sets a Ceiling Post-Training Can't Break

A new controlled study from the LittleLearner project, led by researchers including Ryan Cotterell of ETH Zürich and Wieland Brendel of the Max Planck Institute for Intelligent Systems, found that pos…

07:37
2026-08-16
littlelearner-ll.github.io
large-language-models

What happens when an LLM never sees material beyond fifth grade?

Researchers at the University of Zurich released LittleLearner, a family of language models (0.6B, 1.3B, and 5B parameters) trained from scratch on LittleCurriculum, an 88B-token corpus filtered to U.…

// co-occurs with top 8 entities
LittleLearner 3 FineWeb-Edu 3 LittleCurriculum 2 ETH Zürich 2 Max Planck Institute for Intelligent Systems 2 University of Zurich 1 Ryan Cotterell 1 Wieland Brendel 1
// topics top 4 topics
large language models 3 ai research 3 artificial intelligence 2 machine learning 1