Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting
Xiang Yuan, Kaiqing Lei, Zhenyu Jin +3
The performance of Large Language Models (LLMs) is fundamentally influenced by the distributional composition of multi-domain pre-training data. While manual heuristics were preval…
astro-ph.SR2026
Machine Learning-based Separation of the He I 10830Å Chromospheric Signal: Quantitative Analysis of Chromosphere-Corona Intensity in the Quiet Sun
Huaiming Li, Fangyu Xu, Yi Bi +1
The He I 10830Å line, a crucial optically thin chromospheric line, is frequently used to study coronal heating and vertical coupling across the chromosphere-corona interface. Howev…
cs.CV2026
A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle
Guancheng Zhou, Yisi Luo, Zhengfu He +5
Most current paradigms in visual mechanistic interpretability (MI) remain confined to interpreting internal units of the vision model via heuristic methods (e.g., top- activatio…