3 papers
cs.LG2026
Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +4
Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models su…
cs.LG2026
Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
Akira Ito, Masanori Yamada, Daiki Chijiwa +1
Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output behavior allows t…
cs.LG2025
Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods
Akira Ito, Masanori Yamada, Atsutoshi Kumagai
Recently, Ainsworth et al. showed that using weight matching (WM) to minimize the distance in a permutation search of model parameters effectively identifies permutations tha…