#taskarithmetic
Study shows a one‑epoch fine‑tune yields a vector = –η∇L, linking arithmetic to gradients. Vision benchmarks confirm the first‑epoch gradient dominates, enabling merging. Read more: https://getnews.me/task-vectors-match-gradient-descent-theory-improves-model-merging/ #taskarithmetic #modelmerging
October 3, 2025 at 9:26 AM