Mixture-Trained Merging for Unified Multi-Objective Models
Unified language models are increasingly expected to combine heterogeneous capabilities, such as mathematics, code, instruction following, and controllable thinking behavior, within a single set of parameters. A common solution is sequential post-training on multiple objectives, but this entangles all objectives along...
Seonghyeon Kim, Chaeyun Jang, Seungyoo Lee et al.
· 0 citations