Unverified50% confidenceCautionExact time
The effectiveness of Task Arithmetic is premised on multiple fine-tuned models sharing the same pre-training starting point and cannot be directly applied to two networks independently trained from random initialization.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe method of directly averaging weights sometimes works when two models are fine-tuned from the same initialization, but typically yields poor-performing results for networks independently randomly initialized and trained from scratch.76% similarUnverifiedTraining from scratch means not using any pretrained weights, but instead completing the full training process on a new dataset with randomly initialized parameters.74% similarUnverified多任务学习范式中共享编码器只需提取一次特征，相比独立运行两个完整模型理论上可节省 40%-60% 的计算量73% similarUnverifiedThe study found that jointly training both directions within a single network outperforms training two separate specialized models.72% similarUnverifiedTask Arithmetic, proposed by Ilharco et al. in 2023, obtains task vectors by subtracting pre-trained weights from fine-tuned model weights; adding multiple task vectors together and superimposing them onto the pre-trained weights can combine multi-task capabilities.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968593API
curl https://kongchang.com/api/v1/knowledge/claims/968593MCP
get_claim(id=968593)