CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
year = 1993, month = jul
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A 1B-parameter hierarchical recurrent model pretrained on 40B instruction-response tokens achieves 60.7% MMLU and strong results on ARC-C, DROP, GSM8K, and MATH while using 100-900x fewer tokens than standard baselines.
Neural network learning opacity stems from three dynamical complexity properties in training, rendering some sources of opacity irreducible.
citing papers explorer
-
Child-directed speech facilitates production, not comprehension, in BabyLMs
CDS-trained BabyLMs show earlier and more appropriate production in a new frame-completion task while FineWeb-edu models lead on comprehension benchmarks, indicating current tests underestimate CDS benefits.
-
HRM-Text: Efficient Pretraining Beyond Scaling
A 1B-parameter hierarchical recurrent model pretrained on 40B instruction-response tokens achieves 60.7% MMLU and strong results on ARC-C, DROP, GSM8K, and MATH while using 100-900x fewer tokens than standard baselines.
-
How Complexity Contributes to Learning Opacity in Machine Learning
Neural network learning opacity stems from three dynamical complexity properties in training, rendering some sources of opacity irreducible.