1 citations · 2 across the 6 of their papers we have counts for
4 papers · 1 filter
Mixture-Trained Merging for Unified Multi-Objective Models
SeongHyeon Kim, Chaeyun Jang, Seungyoo Lee +4
Unified language models are increasingly expected to combine heterogeneous capabilities, such as mathematics, code, instruction following, and controllable thinking behavior, withi…
No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation
Seonghyeon Kim, Chaeyun Jang, Noah Lee +2
Multi-teacher on-policy distillation (MOPD) combines independently developed domain teachers into a single student by distilling their predictions on student-generated samples. We…
Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
Mingyeong Kim, Jungwon Choi, Chaeyun Jang +1
Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accurac…
Parallel Test-Time Scaling with Multi-Sequence Verifiers
Yegon Kim, Seungyoo Lee, Chaeyun Jang +2
Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it i…