Differences Visible Even in Small Model Experiments
Turn_Trout · x · 2026-07-13
The author adds that this set of experiments used Qwen2.5-7B, and the dataset size was only 1/5 of that in Anthropic's paper.
This means the relevant conclusions were drawn from a smaller model and dataset, illustrating that even at a modest scale, the training behavior of NLA is significantly influenced by initialization guesses.
More from Research
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11