2 papers
cs.LG2026
Orientation, not magnitude: the causal structure of task-vector interference in merged language models
Chencheng Zhu
Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter…
cs.LG2026
When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition
Chencheng Zhu, Xiaoyang Li, Taotao Cai
Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model func…