SOTAVerified

Task Arithmetic

A task vector specifies a direction in the weight space of a pre-trained model, such that movement in that direction improves performance on the task. We build task vectors by subtracting the weights of a pre-trained model from the weights of the same model after fine-tuning on a task. We show that these task vectors can be modified and combined together through arithmetic operations such as negation and addition, and the behavior of the resulting model is steered accordingly.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 61 papers

TitleStatusHype
Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing—0
Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable ApproachCode0
Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts—0
Soup to go: mitigating forgetting during continual learning with model averaging—0
BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors—0
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach—0
Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach—0
Multi-Task Model Merging via Adaptive Weight DisentanglementCode0
Task Arithmetic Through The Lens Of One-Shot Federated Learning—0
Task Singular Vectors: Reducing Task Interference in Model MergingCode2
Show:102550
← PrevPage 3 of 7Next →

No leaderboard results yet.