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 31–40 of 61 papers

TitleStatusHype
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge—0
Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing—0
Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts—0
Task Arithmetic Through The Lens Of One-Shot Federated Learning—0
Task Arithmetic with LoRA for Continual Learning—0
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse—0
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models—0
Transferring Visual Explainability of Self-Explaining Models through Task Arithmetic—0
What Matters for Model Merging at Scale?—0
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach—0
Show:102550
← PrevPage 4 of 7Next →

No leaderboard results yet.