conftrace_

domain weight

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

specialist model (1) multi-domain capability (1) knowledge distribution (1) expert parameters (1) large language model (1) data composition (1) linear combination (1) multi-domain learning (1) multi-domain training (1) supervised fine-tuning (1)

Papers

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging ICML 2025 VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs EMNLP 2025